Molecular evolution is the process of simulating the natural evolution of molecules in chemical space to explore potential molecular structures and properties. The relationships between similar molecules are often described through transformations such as adding, deleting, and modifying atoms and chemical bonds, reflecting specific evolutionary paths. Existing molecular representation methods mainly focus on mining data, such as atomic-level structures and chemical bonds directly from the molecules, often overlooking their evolutionary history. Consequently, we aim to explore the possibility of enhancing molecular representations by simulating the evolutionary process. We extract and analyze the changes in the evolutionary pathway and explore combining it with existing molecular representations. Therefore, this paper proposes the molecular evolutionary network (MEvoN) for molecular representations. First, we construct the MEvoN using molecules with a small number of atoms and generate evolutionary paths utilizing similarity calculations. Then, by modeling the atomic-level changes, MEvoN reveals their impact on molecular properties. Experimental results show that the MEvoN-based molecular property prediction method significantly improves the performance of traditional end-to-end algorithms by approximately 33% on both the QM7 and QM9 datasets.

The prediction of compound–protein interactions (CPIs) is crucial for drug discovery. Most existing CPI prediction models rely on protein sequence information as input. However, in early-stage drug development, particularly in phenotype-driven studies or compound-response analyses, proteins are often annotated only with functional labels, and their sequences remain undetermined. Consequently, current methods are inapplicable in such scenarios. Furthermore, our experiments find that even when large-scale perturbations were applied to protein sequences, the predictive performance of the existing models did not show a significant decline. It indicates that the high investment in sequencing may not bring corresponding returns. To address the above issues, we propose an inexpensive, protein-sequencing-free framework BioText-CPI, based on the Biomedical Textual description of protein for CPI prediction. Firstly, during the pre-training stage of the model, we use contrastive learning to align protein texts and sequence modalities. Subsequently, we add biological text descriptions of proteins to the existing public CPI dataset to construct a new CPI dataset. Finally, in the CPI prediction stage, the sequence and biomedical text descriptions of proteins can be used as the input for CPI prediction either separately or simultaneously to meet the application requirements of different scenarios. The experiments demonstrate that BioText-CPI achieves comparable effects to the traditional methods when only the biomedical description of protein is input. Moreover, when the two modalities of protein information are input simultaneously, BioText-CPI achieves state-of-the-art performance across multiple scenarios.

Hypergraph-based distillation methods have been proposed to mitigate the high computational cost of Hypergraph Neural Networks (HGNNs) in modeling high-order relationships. However, most existing methods use static and uniform distillation strategies for all nodes and hyperedges, ignoring their individual characteristics. In addition, they neglect the student model's capability to independently extract useful internal features. As a result, they are not effective in transferring higher-order structural knowledge from the teacher. To overcome these limitations, we propose ARCHER, an Adaptive and Reinforcement-Guided Contrastive HypER graph Distillation framework that enables a lightweight MLP student model to outperform its HGNN teacher model. First, we design an adaptive strategy that leverages node- and hyperedge-level confidence to mediate error guidance from the teacher model. Second, we introduce a contrastive learning module that guides the student to learn from both the teacher's outputs and its own internal representations, producing more expressive embeddings. Finally, we propose a multi-armed bandit-based reinforcement learning module that dynamically balances multiple loss objectives during training. Experiments on six benchmark datasets demonstrate that our method outperforms existing hypergraph distillation methods.

Existing multi-behavior recommendations tend to prioritize performance at the expense of explainability, while current explainable methods suffer from limited generalizability due to their reliance on external information. Neuro-Symbolic integration offers a promising avenue for explainability by combining neural networks with symbolic logic rule reasoning. Concurrently, we posit that user behavior chains (e.g., view->cart->buy) inherently embody an endogenous logic suitable for explicit reasoning. However, these observational multiple behaviors are plagued by confounders, causing models to learn spurious correlations. By incorporating causal inference into this Neuro-Symbolic framework, we propose a novel Causal Neuro-Symbolic Reasoning model for Explainable Multi-Behavior Recommendation (CNRE). CNRE operationalizes the endogenous logic by simulating a human-like decision-making process. Specifically, CNRE first employs hierarchical preference propagation to capture heterogeneous cross-behavior dependencies. Subsequently, it models the endogenous logic rule implicit in the user's behavior chain based on preference strength, and adaptively dispatches to the corresponding neural-logic reasoning path (e.g., conjunction, disjunction). This process generates an explainable causal mediator that approximates an ideal state isolated from confounding effects. Extensive experiments on three large-scale datasets demonstrate CNRE's significant superiority over state-of-the-art baselines, offering multi-level explainability from model design and decision process to recommendation results.

Graph Masked Autoencoders (GMAEs) have emerged as a notable self-supervised learning approach for graph-structured data. Existing GMAE models primarily focus on reconstructing node-level information, categorizing them as single-scale GMAEs. This methodology, while effective in certain contexts, tends to overlook the complex hierarchical structures inherent in many real-world graphs. For instance, molecular graphs exhibit a clear hierarchical organization in the form of the atoms-functional groups-molecules structure. Therefore, the inability of single-scale GMAE models to incorporate these hierarchical relationships often results in an inadequate capture of crucial high-level graph information, leading to a noticeable decline in performance. To address this limitation, we propose Hierarchical Graph Masked AutoEncoders (Hi-GMAE), a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. First, Hi-GMAE constructs a multi-scale graph hierarchy through graph pooling, enabling the exploration of graph structures across different granularity levels. To ensure masking uniformity of subgraphs across these scales, we propose a novel coarse-to-fine strategy that initiates masking at the coarsest scale and progressively back-projects the mask to finer scales. Furthermore, we integrate a gradual recovery strategy with the masking process to mitigate the learning challenges posed by completely masked subgraphs. Diverging from the standard graph neural network (GNN) used in GMAE models, Hi-GMAE modifies its encoder and decoder into hierarchical structures. This entails using GNN at the finer scales for detailed local graph analysis and employing a graph transformer at coarser scales to capture global information. Such a design enables Hi-GMAE to effectively capture the multi-level information inherent in complex graph structures. Our experiments on 17 graph datasets, covering two graph learning tasks, consistently demonstrate that Hi-GMAE outperforms 29 state-of-the-art self-supervised competitors in capturing comprehensive graph information.

Recently, hypergraph knowledge distillation has been proposed to alleviate the high computational cost of Hypergraph Neural Networks (HGNNs) when modeling high-order relationships in Web-related graph tasks. Its effectiveness primarily depends on the quality of knowledge transferred from the teacher and the representation capability of the student. However, existing methods remain limited on both sides. On the teacher side, most methods typically rely on a single HGNN teacher, which provides limited structural and semantic knowledge, thereby constraining the upper bound of the student's performance. The potential of exploiting multiple teachers in HGNNs remains largely underexplored. On the student side, existing methods ignore the student's capability to capture high-order semantic and structural information beyond simply imitating teacher outputs, leading to limited representation learning. To address these limitations, we propose MARCH, a framework for Multi-TeAcheR Contrastive Hypergraph Distillation, which advances semantic modeling and distillation for Web-scale structured data. Specifically, MARCH proposes a multi-teacher distillation strategy that adaptively transfers complementary knowledge from multiple teachers at both node and hyperedge levels, empowering the student model to learn richer and more discriminative representations and even outperform its teachers. Extensive experiments on six benchmark datasets demonstrate the superior performance of MARCH.

Graph-level anomaly detection (GLAD) is a critical task to identify graphs with abnormal properties in various domains, ranging from fraudulent social networks to malicious botnets on online platforms. The dominant paradigm for existing GLAD detectors has been partially unsupervised, relying on training data composed exclusively of normal samples. However, this partially unsupervised paradigm inevitably requires a costly expert filtering process to ensure the training data is free of anomalies. This creates a significant gap between current approaches and the real-world necessity of a fully unsupervised paradigm, which involves training a model directly on real-world data ''as-is'', with its inherent mix of normal and anomalous samples. To bridge this gap, we incorporate uncertainty learning into GLAD to promote fully unsupervised learning. We propose two frameworks: Score Uncertainty Learning (SUL) and Graph-data Uncertainty Learning (GUL). Specifically, SUL enhances existing GLAD detectors by modeling uncertainty through Gaussian distributions over the detectors' predictions, adaptively attenuating the influence of potential anomalies. GUL is an end-to-end framework that iteratively optimizes anomaly detection and uncertainty modeling via an Expectation-Maximization algorithm. In addition, we develop a dedicated loss that utilizes potential anomalies to enhance the effectiveness and robustness of GUL. Empirical results on sixteen benchmark datasets, covering real-world graphs from social networks and online platforms, demonstrate the superiority of our methods and highlight the promise of incorporating uncertainty into fully unsupervised GLAD.

Multi-task learning (MTL) is a standard learning paradigm in machine learning. The central idea of MTL is to capture the shared knowledge among multiple tasks for mitigating the problem of data sparsity where the annotated samples for each task are quite limited. Recent studies indicate that graph multi-task learning (GMTL) yields the promising improvement over previous MTL methods. GMTL represents tasks on a task relation graph, and further leverages graph neural networks (GNNs) to learn complex task relationships. Although GMTL achieves the better performance, the construction of task relation graph heavily depends on simple heuristic tricks, which results in the existence of spurious task correlations and the absence of true edges between tasks with strong connections. This problem largely limits the effectiveness of GMTL. To this end, we propose the Generative Causality-driven Network (GCNet), a novel framework that progressively learns the causal structure between tasks to discover which tasks are beneficial to be jointly trained for improving generalization ability and model robustness. To be specific, in the feature space, GCNet first introduces a feature-level generator to generate the structure prior for reducing learning difficulty. Afterwards, GCNet develops a output-level generator which is parameterized as a new causal energy-based model (EBM) to refine the learned structure prior in the output space driven by causality. Benefiting from our proposed causal framework, we theoretically derive an intervention contrastive estimation for training this causal EBM efficiently. Experiments are conducted on multiple synthetic and real-world datasets. Extensive empirical results and model analyses demonstrate the superior performance of GCNet over several competitive MTL baselines.

Social event detection (SED) involves identifying and analyzing significant real-world events using data generated on social media platforms. With the rapid growth of platforms like Weibo and Twitter, users are sharing not just text but also images. However, most existing SED methods remain text-focused, limiting their ability to fully capture the complexity of real-world social dynamics. Moreover, the lack of multi-modal datasets specifically designed for SED has blocked the development of models that can effectively exploit these rich content types. To address these limitations, we introduced WEIBO2022, an extensive multi-modal SED dataset that includes both text and image data. The dataset is available in two versions: WEIBO2022-Medium, containing 25,435 entries and WEIBO2022-Large, containing 79,825 entries. In addition, we presented a novel network called the Key Instance-driven, Quality-aware Graph Neural Network (KQGNN), which features a key instance-driven library, a quality-aware learning process, and a multi-modal fusion module, enhancing its ability to detect events accurately in both offline and real-time settings. Extensive experiments showcase the exceptional performance and superiority of the proposed model, showing improvements in detection accuracy and effective prevention of catastrophic forgetting during continuous training.

Brain graphs (brain connectivity networks) play an important role in modeling the complex structure of the human brain. Furthermore, brain graph learning based on graph neural networks (GNNs) has recently attracted growing interest. Although existing methods have made great progress in brain disorder prediction and pathogenic analysis, there are two key problems: (1) They rarely utilize the pathogenic reason of brain disorders, that is, salient brain regions always lead to abnormal connections between brain regions, to extract critical brain graph information for disorder analysis; (2) Since most of the available brain graph data is limited, how can we improve the performance of brain graph learning models on insufficient training data? Thus, in this paper, we learn brain graph representations for disorder prediction and analyze disorder-specific brain regions and connections from the subgraph perspective. Besides, we introduce the cross-domain brain graph learning framework to alleviate the problem of poor model performance on limited data. To consider the pathogenic reason by brain subgraphs, we first propose the node entropy of brain graphs based on brain graph properties to extract important nodes. We then introduce subgraph information bottleneck to refine the critical subgraph from the rough subgraph generated by these important nodes, recognizing important connections related to disorders. To achieve a better model performance on limited data, we design a cross-domain brain graph learning framework to improve the subgraph extraction model by the meta-learning method. The subgraph extraction model is pre-trained on a large source training dataset and then quickly adapted to target task dataset. Besides, a simple yet effective feature alignment module is applied to mitigate the negative transfer problem for cross-domain datasets. Extensive experimental results, including disorder prediction and pathogenic analysis on real-world neuroimaging data, demonstrate the effectiveness of our method.

LiDAR is one of the most important sensors in the field of autonomous driving and allows for better and more accurate perception of the changes in the surrounding environment. Most of the existing 3D object detection methods use data augmentation and feature fusion enhancement to improve the performance of detection, but the majority of the methods ignore the handling of sample imbalance problems during data augmentation. Also, the designed feature fusion and enhancement methods were not well suited to work with the enhancement methods. To this end, we developed a combined method involving data augmentation and feature enhancement. The designed approach has two main objectives: 1) to address the problem of unbalanced sample distribution in detection scenes through data augmentation, and 2) to enhance feature perception using a special feature enhancement module. Our proposed method solves the problem of class imbalance by directly increasing the number of pedestrian samples in the scene through mixed data augmentation, i.e., RG-Aug. In addition, we introduce the Decoupling and Attention Fusion module (DAF), which combines classification headers with high-level features and prediction branches with low-level features. Leverage data features between different layers of features to get a more robust feature representation. Finally, the multi-scale pyramid attention enhancement module is designed to achieve feature enhancement of multi-scale features by means of attention to improve the detection ability of small objects in the scene, especially the detection ability of pedestrians. Our method can achieve 1.57%, 2.16%, and 2.05% performance improvement on the KITTI dataset for Easy, Mod, and Hard samples, respectively. Furthermore, for the detection of pedestrians, our method has a significant competitive advantage over other state-of-the-art techniques with a mAP of 73.42%.

Graph-level anomaly detection (GLAD) aims to identify graphs that significantly deviate from others in a graph dataset. Existing methods predominantly rely on standard Graph Neural Networks (GNNs) to learn graph representations, but they often overlook subgraph-level information, which provides essential structural and semantic cues for distinguishing normal and anomalous graphs. This limitation not only compromises the detection performance but also hinders the interpretability of GLAD predictions. To address these challenges, we propose NGLAD, a novel framework that introduces the concept of normality-relevant subgraphs that capture shared patterns across normal graphs. These subgraphs serve as key indicators to distinguish normal graphs from anomalies that that often lack or deviate from such patterns. During model training, by explicitly modeling the shared subgraph patterns inherent in normal graphs through a Subgraph Extractor and a Normality Learner, NGLAD identifies the subgraphs most relevant to normality. Leveraging the One-class Information Bottleneck principle, these modules ensure that the extracted subgraphs retain only the most informative features of normality while filtering out irrelevant nodes and edges. During inference, NGLAD detects anomalies by evaluating inconsistencies in representations between the input graph and its extracted subgraph. Extensive evaluations on synthetic and real-world datasets demonstrate that NGLAD significantly outperforms state-of-the-art methods in detection performance while offering interpretable explanations.

Graph Neural Networks (GNNs) have been widely used for learning representations of graph-structured data, achieving remarkable success in various graph-related Web applications, such as fraud detection. To generate node representations, GNN-based models operate message-passing mechanisms that aim to smooth the learned representations in a local neighborhood. However, fraudsters increasingly employ sophisticated “camouflage” tactics, exhibiting normal behaviors by strategically forming numerous connections with legitimate entities. As a result, existing GNN-based methods struggle to effectively tackle such fraudulent activities due to their reliance on homophily-based message-passing architectures. These methods fail to generate discriminative representations, which is crucial for distinguishing fraudsters from benign entities. To address this problem, we propose a novel Discriminative Enhanced Aggregation Graph Neural Network-based FraudDEtectioNMoDel (DEFEND) . DEFEND incorporates tailored discriminative mechanisms that strengthen representation learning at two complementary levels: (i) intra-relation and (ii) inter-relation. While prior approaches primarily focus on intra-relation patterns and overlook inter-relation information, DEFEND integrates both to capture subtle inconsistencies in fraudster behavior. Specifically, an edge discriminating mechanism classifies neighborhoods into homophily or heterophily-based views by leveraging node attributes and structural characteristics, and a camouflage-aware dual-channel aggregation module captures different frequencies of information tailored to these views to generate rich intra-relation node representations. While prior approaches typically rely on intra-relation information within each relation type, they overlook the discriminative signals that arise from correlations across different relations. In DEFEND, we observe that fraudsters often avoid forming consistent cross-relation interactions, whereas benign entities tend to establish them more frequently. This discrepancy creates a distinctive behavioral pattern. To capture this, we introduce an inter-relation correlation mechanism that correlates a node’s intra-relation representations across multiple relation types using an attention-based weighting scheme. By adaptively weighing the importance of each relation and integrating their contributions, DEFEND enhances the discriminative power of node representations. This mechanism enables the model to leverage both intra-relation and inter-relation levels of information, leading to richer and more robust representations for fraud detection. Finally, a multi-relation combination module aggregates information across different relation types, emphasizing the importance of node–relation pairs in the embedding. We conducted extensive experiments on two real-world fraud datasets to demonstrate the effectiveness of our proposed model, and our results show that DEFEND outperforms the state-of-the-art baselines. The source codes and datasets of our work are available at https://github.com/VenusHaghighi/DEFEND .

Arbitrary-oriented object detection remains a pivotal research focus due to its practical significance and inherent challenges. Existing methods often extend frameworks and sampling strategies designed for horizontal object detectors, which struggle to handle the arbitrary orientations, high aspect ratios, and diverse scales of oriented objects. To overcome these limitations, we propose a novel and efficient method for arbitrary-oriented object detection. This approach dynamically assigns prediction layers by object pixel area, then leverages wavelet transform-based energy weighting for bottom-up sample reassignment, optimizing feature representation for oriented targets. In addition, a robust framework integrates heatmap keypoint prediction on feature maps of a quarter-sized image, along with sparse predictions on other scales. By querying small-object regions within deep feature maps, a progressive top-down feature fusion strategy further enhances the perception of fine-grained details. Extensive evaluations on four benchmark datasets demonstrate the method's substantial improvements in detection performance, establishing its potential for broader applications in oriented object detection.

Understanding the complex relationships and behavioral preferences among users in social networks is crucial for elucidating the mechanisms of information diffusion. While recent information diffusion prediction methods, empowered by graph neural networks, have advanced the learning of user representations, they rarely exploit spread interaction feedback. This feedback reflects users' interests in engaging with information and serves as a key driver of information diffusion. Moreover, the underutilization of unlabeled data leads to an overreliance on labeled data, consequently constraining the model's self-learning and generalization capabilities. To address these limitations, we propose a novel microscopic diffusion prediction model based on interaction-enhanced graph neural sequence contrastive learning (IEGSCL). Specifically, we construct a triple graph to explore the diversity of user relationships and preferences through the lenses of trust and interaction. A self-supervised graph contrastive learning module is designed to transfer user intents, maximizing the utility of unlabeled data and tackling the feature extraction challenge. Furthermore, we devise an information-driven gating strategy that adaptively modulates the contributions of social and interactive intents to cascade participation, thereby effectively integrating interaction feedback into the cascade modeling. Finally, we employ maximum mean discrepancy (MMD) to enforce distributional consistency between global relationship representations and local cascade encodings. Extensive experiments on four public datasets validate the superior performance of the proposed model over existing baselines.

Industrial applications involving digital twins (e.g., behavior simulation) demand highly accurate, low-latency data, making real-time data acquisition critical. To meet performance demands, devices that do not support asynchronous communication need to acquire data at high frequency. In cloud-edge collaboration schemes, edge computing nodes typically acquire the data. However, high-frequency data acquisition and processing impose considerable costs, posing significant challenges for these resource-constrained nodes. To address this problem, we propose a model called Cost-minimized Data Edge Access (CDEA) that can dynamically minimize the edge costs while satisfying long-term performance requirements. CDEA quantifies data performance by decomposing the workflow of industrial systems into basic action units. These units are used to model data acquisition, data processing, data transmission, and cloud computing. Then, a cost minimization problem is formulated based on these components. To address irregular data changes and the general lack of available statistics on system’s network status, the framework incorporates Lyapunov optimization to transform the long-term guarantee over data performance into a series of instantaneous decision problems. Finally, a heuristic algorithm identifies the optimal data acquisition strategy. To validate CDEA’s effectiveness, we implemented it in two representative digital twin scenarios: cathode plate stripping and AGV transportation. Experimental results demonstrate that CDEA can indeed reduce both edge costs and cloud resources consumption while still ensuring high data performance.

Recommender systems in various applications often encounter the challenge of cold-start, which refers to how to provide recommendations for completely new users. Cross-domain recommendation offers a solution to address this cold-start issue by leveraging user interaction information from other domains and providing recommendations for users in the target domain. However, applying the classic two-tower model in cross-domain scenarios for pure cold-start users proves challenging, and most existing cross-domain cold-start recommendation models adopt an embedding-mapping framework that lacks end-to-end efficiency. The parallel training recommendation method lacks consideration of the domain-level intrinsic characteristics of cross-domain information. In this paper, we propose a generalized framework that Domain-level Disentanglement framework based on information enhancement for Cross-domain Cold-start Recommendation. On one hand, we achieve deep utilization of domain-level information through independent extraction of domain knowledge and fusion using heuristic strategies. On the other hand, our model is incorporated with an information enhancement network based on user attention and a user personalized adaptor. We introduce measures to assess user variability and immutability in cross-domain recommendation, aiming to eliminate inter-domain bias and highlight individual user preferences. Experimental results on widely used cross-domain recommendation datasets demonstrate that our proposed model outperforms state-of-the-art methods, validating its effectiveness.

Social event detection involves identifying and categorizing important events from social media, which relies on labeled data, but annotation is costly and labor-intensive. To address this problem, we propose Augmentation framework for Social Event Detection (SED-Aug), a plug-and-play dual augmentation framework, which combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness. The explicit augmentation utilizes LLMs to enhance textual information through five diverse generation strategies. For implicit augmentation, we design five novel perturbation techniques that operate in the feature space on structural fused embeddings. These perturbations are crafted to keep the semantic and relational properties of the embeddings and make them more diverse. Specifically, SED-Aug outperforms the best baseline model by approximately 17.67% on the Twitter2012 dataset and by about 15.57% on the Twitter2018 dataset in terms of the average F1 score.

Social event detection (SED) is the task of identifying, categorizing, and tracking events from social data sources such as social media posts, news articles, and online discussions.Existing state-of-the-art (SOTA) SED models predominantly rely on graph neural networks (GNNs), which involve complex graph construction and time-consuming training processes, limiting their practicality in real-world scenarios.In this paper, we rethink the key challenge in SED: the informal expressions and abbreviations of short texts on social media platforms, which impact clustering accuracy.We propose a novel framework, LLM-enhanced Social Event Detection (LSED), which leverages the rich background knowledge of LLMs to address this challenge.Specifically, LSED utilizes LLMs to formalize and disambiguate short texts by completing abbreviations and summarizing informal expressions.Furthermore, we introduce hyperbolic space embeddings, which are more suitable for natural language sentence representations, to enhance clustering performance.Extensive experiments on two challenging realworld datasets demonstrate that LSED outperforms existing SOTA models, achieving improvements in effectiveness, efficiency, and stability.Our work highlights the potential of LLMs in SED and provides a practical solution for real-world applications.The code is available at GitHub 1 .

Spatio-temporal graphs encode dynamic interactions across space and time, but their size and complexity pose challenges for analysis and computation. Graph sparsification provides an effective solution to these issues by reducing the number of edges while preserving the essential structural and dynamic properties of the network. This reduction is crucial for enhancing the interpretability of complex graphs, revealing hidden patterns, and enabling more efficient computational analysis. However, real-world graphs often exhibit continuous spatial and temporal evolution, which most existing sparsification algorithms, primarily designed for static graphs, fail to address. We introduce STGS (Spatio-Temporal Graph Sparsification), a reinforcement learning-based framework for sparsifying spatio-temporal graphs. By learning to prune edges while preserving key spatio-temporal patterns, STGS enables efficient analysis of evolving systems. Experiments on real-world datasets demonstrate that STGS outperforms existing methods in both structural preservation and downstream forecasting tasks.

In an era where misinformation spreads freely, factchecking (FC) plays a crucial role in verifying claims and promoting reliable information.While automated fact-checking (AFC) has advanced significantly, existing systems remain vulnerable to adversarial attacks that manipulate or generate claims, evidence, or claim-evidence pairs.These attacks can distort the truth, mislead decision-makers, and ultimately undermine the reliability of FC models.Despite growing research interest in adversarial attacks against AFC systems, a comprehensive, holistic overview of key challenges remains lacking.These challenges include understanding attack strategies, assessing the resilience of current models, and identifying ways to enhance robustness.This survey provides the first in-depth review of adversarial attacks targeting FC 1 , categorizing existing attack methodologies and evaluating their impact on AFC systems.Additionally, we examine recent advancements in adversary-aware defenses and highlight open research questions that require further exploration.Our findings underscore the urgent need for resilient FC frameworks capable of withstanding adversarial manipulations in pursuit of preserving high verification accuracy.Attack Target Edit Granularity Attack Technique Claim attack Evidence attack Claim-evidence pair attack Generate Manipulate Generate Manipulate

Due to their excellent drug-like and pharmacokinetic properties, small molecule drugs are widely used to treat various diseases, making them a critical component of drug discovery. In recent years, with the rapid development of deep learning (DL) techniques, DL-based small molecule drug discovery methods have achieved excellent performance in prediction accuracy, speed, and complex molecular relationship modeling compared to traditional machine learning approaches. These advancements enhance drug screening efficiency, streamline optimization, and provide more precise and effective solutions for drug discovery. Contributing to this field's development, this paper aims to systematically summarize and generalize the recent key tasks and representative techniques in graph-structured small molecule drug discovery. Specifically, we provide an overview of the major tasks in small-molecule drug discovery and their interrelationships. Next, we analyze the six core tasks, summarizing the related methods, commonly used datasets, and technological development trends. Finally, we discuss key challenges, such as interpretability and out-of-distribution generalization, and offer our insights into future research directions for small molecule drug discovery.

The effective organization and utilization of dis-persed archival resources remain a significant challenge in archival management services. This paper proposes a structured graph-based knowledge modeling framework to transform dispersed archival records into a structured knowledge system for enhanced analysis and knowledge discovery. The framework uncovers latent knowledge embedded within archival records by applying metadata extraction, semantic annotation, ontology construction, and graph-based visualization methods. Specifically, we first design a metadata schema that integrates both standard and customized elements to maximize the machine-readable representation of archival content. Based on this schema, a domain ontology comprising five core classes is constructed to systematically represent the semantic structure of the archival collection. Secondly, we develop an intelligent processing platform to handle multimodal resources, supporting automatic metadata extraction, manual annotation, and comprehensive data prepro-cessing. Lastly, we take unstructured COVID-19-related archival materials as a case study to demonstrate how the system organizes and links archival knowledge, which significantly improves the retrieval, reuse, and discovery of valuable resources.

Antibody design remains a critical challenge in therapeutic and diagnostic development, particularly for complex antigens with diverse binding interfaces. Current computational methods face two main limitations: (1) capturing geometric features while preserving symmetries, and (2) generalizing novel antigen interfaces. Despite recent advancements, these methods often fail to accurately capture molecular interactions and maintain structural integrity. To address these challenges, we propose AbMEGD, an end-to-end framework integrating Multi-scale Equivariant Graph Diffusion for antibody sequence and structure co-design. Leveraging advanced geometric deep learning, AbMEGD combines atomic-level geometric features with residue-level embeddings, capturing local atomic details and global sequence-structure interactions. Its E(3)-equivariant diffusion method ensures geometric precision, computational efficiency, and robust generalizability for complex antigens. Furthermore, experiments using the SAbDab database demonstrate a 10.13% increase in amino acid recovery, 3.32% rise in improvement percentage, and a 0.062 Å reduction in root mean square deviation within the critical CDR-H3 region compared to DiffAb, a leading antibody design model. These results highlight AbMEGD's ability to balance structural integrity with improved functionality, establishing a new benchmark for sequence-structure co-design and affinity optimization. The code is available at: https://github.com/Patrick221215/AbMEGD.

Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to effectively extract features in block-wise missing data scenarios. Meanwhile, the static graph structure for spatial feature propagation significantly constrains the model's flexibility in handling the distribution shift issue for the nonstationary traffic data. To address these issues, this paper proposes a Spatio-Temporal Attention Mixture of experts network named STAMImputer for traffic data imputation. Specifically, we introduce a Mixture of Experts (MoE) framework to capture latent spatio-temporal features and their influence weights, effectively imputing block missing. A novel Low-rank guided Sampling Graph ATtention (LrSGAT) mechanism is designed to dynamically balance the local and global correlations across road networks. The sampled attention vectors are utilized to generate dynamic graphs that capture real-time spatial correlations. Extensive experiments are conducted on four traffic datasets for evaluation. The result shows STAMImputer achieves significantly performance improvement compared with existing SOTA approaches. Our codes are available at https://github.com/RingBDStack/STAMImupter.

Text-attributed graph (TAG) provides a text description for each graph node, and few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. Existing work utilizes various graph-based augmentation techniques to train the node and text embeddings, while text-based augmentations are largely unexplored. In this paper, we propose Text Semantics Augmentation (TSA) to improve accuracy by introducing more text semantic supervision signals. Specifically, we design two augmentation techniques, i.e., positive semantics matching and negative semantics contrast, to provide more reference texts for each graph node or text description. Positive semantic matching retrieves texts with similar embeddings to match with a graph node. Negative semantic contrast adds a negative prompt to construct a text description with the opposite semantics, which is contrasted with the original node and text. We evaluate TSA on 5 datasets and compare with 13 state-of-the-art baselines. The results show that TSA consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%. The code is at https://github.com/wyx11112/TSA.

Retrosynthesis prediction aims to infer the precursor compounds and synthetic pathways for the given product molecule. Despite the emergence of numerous data-driven template-free approaches, most rely on single-modality inputs (e.g., SMILES or molecular graphs), limiting them to incorporate multimodal information. Besides, existing methods require complex alignment preprocessing for models to capture unaltered molecular structures in reactions, which rigidly restricts the data format and hinders generalizing to practical application scenarios. To address these challenges, this paper proposes a novel end-to-end template-free learning framework, named Cross-modal Fine-grained Contrastive Learning for Retrosynthesis Prediction (CFC-Retro). By taking both sequence and graph data as inputs, CFC-Retro leverages the cross-attention mechanism to effectively integrate multimodal information during encoding. Additionally, CFC-Retro employs multimodal hybrid-enhanced decoding to produce accurate results. Moreover, the contrastive learning strategy in CFC-Retro implicitly aligns multimodal features at the atomic level. This strategy guides the model to perceive molecular structural changes in chemical reactions, while exhibiting high flexibility. Experiments show that CFC-Retro achieves top-1 accuracy of 53.7% and validity of 99.7% on USPTO-50k with reaction class unknown, underscoring its robust performance in retrosynthesis prediction.

Graph-level anomaly detection (GLAD) identifies graphs exhibiting abnormal properties within a graph dataset.Despite promising results in this task, the state-of-the-art methods cannot be fully trusted and deployed in realistic scenarios due to their black-box nature.To alleviate this, existing methods try to explain predictions by extracting important subgraphs from each graph, as instancelevel explanations.However, instance-level explanations across all samples are costly to verify and insufficient to capture the model's general behaviors.Thus, we propose a global interpretable Graph-Level Anomaly Detection model via Prototype (GLADPro), which provides global-level explanations throughout the entire dataset, that is, the significant subgraph patterns that consistently influence the model's decisions.Specifically, GLADPro incorporates prototype learning with the information bottleneck principle, enabling prototypes to capture the most significant subgraph patterns as global-level explanations through persistent interactions with key subgraphs from input graphs.In addition, a regularization term is proposed to prevent the collapse traps with theoretical proof.Finally, we filter redundant prototypes using the maximum mean discrepancy metric.Extensive experiments demonstrate the superiority of GLADPro in anomaly detection and explainability; for instance, on the mutagen dataset, it reduces the number of explanations to verify from 1403 to only 6.

Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding. Existing graph-based superpixel segmentation methods typically concentrate on the relationships between a given pixel and its directly adjacent pixels while overlooking the influence of non-adjacent pixels. These approaches do not fully leverage the global information in the graph, leading to suboptimal segmentation quality. To address this limitation, we present SIT-HSS, a hierarchical superpixel segmentation method based on structural information theory. Specifically, we first design a novel graph construction strategy that incrementally explores the pixel neighborhood to add edges based on 1-dimensional structural entropy (1D SE). This strategy maximizes the retention of graph information while avoiding an overly complex graph structure. Then, we design a new 2D SE-guided hierarchical graph partitioning method, which iteratively merges pixel clusters layer by layer to reduce the graph’s 2D SE until a predefined segmentation scale is achieved. Experimental results on three benchmark datasets demonstrate that the SIT-HSS performs better than state-of-the-art unsupervised superpixel segmentation algorithms. The source code is available at https://github.com/SELGroup/SIT-HSS.

Recently, diffusion model-based methods have utilized user interest features as guidance conditions to achieve stable generation results in sequential recommendation tasks. However, these models struggle to capture users' dynamic interests, as the interests of different users are often inconsistent. Moreover, the fixed number of interests predefined by existing models cannot adapt to the diverse preferences of users, making it difficult to further improve recommendation performance. To address these issues, we propose a novel generative sequential recommendation framework named ADIGRec (Adaptive User Dynamic Interest Guidance for Generative Sequential Recommendation), which adaptively focuses on users' dynamic interest features. Specifically, our framework combines users' dynamic features and inherent interest features encoded from historical sequences as new guidance conditions. Furthermore, we introduce a module that injects dynamic interest features into the noise item embeddings, enabling explicit interaction with the guidance conditions during the generation phase. This approach essentially fits the noise in the target space rather than the user preference space, leading to improved recommendation diversity. Additionally, we propose a novel regularization method to mitigate the impact of user interest routing collapse on the generation results. Extensive experiments on three publicly available datasets demonstrate that our method achieves superior performance compared to established baseline methods.

Graph-level out-of-distribution (OOD) detection, which attempts to identify OOD graphs originated from an unknown distribution, is a vital building block for safety-critical applications in Web and society. Current approaches concentrate on how to learn better graph representations, but fail to provide any statistically guarantee on detection results, therefore impeding their deployments in the scenario where detection errors would result in serious consequences. To overcome this critical issue, we propose the Conformal Graph-level Out-of-distribution Detection (CGOD), extending the theory of conformal prediction to graph-level OOD detection with a rigorous control over the false positive rate. In CGOD, we develop a new aggregated non-conformity score function based on the proposed adaptive data augmentation. Through the guidance from two designed metrics, i.e., score consistency and representation diversity, our augmentation strategy can generate multiple non-conformity scores, and aggregating these generated non-conformity scores together is robust to the misleading information. Meanwhile, our score function can perceive the subsequent process of conformal inference, enabling the aggregated non-conformity score to be adaptive to different input graphs and deriving a more accurate score estimation. We conduct experiments on multiple real-world datasets with different empirical settings. Extensive results and model analyses demonstrate the superior performance of our approach over several competitive baselines.

Abstract Fraud detection in online networks has become increasingly challenging as fraudsters adopt sophisticated camouflage tactics to evade detection, making it imperative to combat their deceptive strategies. Graph-based fraud detection has gained significant attention in recent years, reflecting its growing potential to mitigate sophisticated fraudulent activities. The main objective of graph-based fraud detection is to distinguish between fraudsters and normal entities within graphs. While real-world networks contain complex, high-order relationships, existing graph-based fraud detection methods focus solely on pairwise interactions, overlooking non-pairwise relationships and the broader dependencies among entities within fraud graphs. Thus, we highlight the importance of exploring non-pairwise relationships to build a more effective fraud detection model. In this paper, we propose TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng framework for detecting CAmouflaged maLicious actors in online social networks. To capture comprehensive high-order relations, we construct a hypergraph from the original input graph. However, constructing the hypergraph can be computationally intensive. TROPICAL addresses this challenge by carefully selecting moderate hyperparameters, creating a balance between computational efficiency and effectively capturing high-order relationships. TROPICAL learns node representations by processing multiple hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. The aggregated sequential information is then passed through a transformer encoder, enabling the model to generate rich, high-order representations to detect camouflaged fraudsters. Extensive experiments on two real-world datasets demonstrate TROPICAL’s superior performance compared to the state-of-the-art fraud detection models. The source codes and the datasets of our work are available at https://github.com/VenusHaghighi/TROPICAL .

Nowadays social media is the primary platform for people to obtain news and share information. Combating online fake news has become an urgent task to reduce the damage it causes to society. Existing methods typically improve their fake news detection performances by utilizing textual auxiliary information (such as relevant retweets and comments) or simple structural information ( i.e. , graph construction). However, these methods face two challenges. First, an increasing number of users tend to directly forward the source news without adding comments, resulting in a lack of textual auxiliary information. Second, simple graphs are unable to extract complex relations beyond pairwise association in a social context. Given that real-world social networks are intricate and involve high-order relations, we argue that exploring beyond pairwise relations between news and users is crucial for fake news detection. Therefore, we propose constructing an attributed hypergraph to represent non-textual and high-order relations for user participation in news spreading. We also introduce a hypergraph neural network-based method called Hy-DeFake to tackle the challenges. Our proposed method captures semantic information from news content, credibility information from involved users, and high-order correlations between news and users to learn distinctive embeddings for fake news detection. The superiority of Hy-DeFake is demonstrated through experiments conducted on four widely-used datasets, and it is compared against nine baselines using four evaluation metrics. • We introduce an approach named Hy-DeFake by constructing an attributed hypergraph to represent the process of news spreading in online social networks. By abstracting fake news detection as hyperedge classification, we capture the intricate high-order relation between news and users in social contexts, enabling us to achieve accurate results. • The proposed Hy-DeFake utilizes hypergraph neural networks for fake news detection. It effectively captures the credibility information of users and the high-order correlation between news and users. Both of these aspects provide distinctive information that contributes to fake news detection. • Extensive experiments demonstrate that Hy-DeFake generally surpasses nine baseline methods on four real-world datasets from different domains. • We verify the positive correlation between news authenticity and user credibility. Users who spread fake news exhibit more intensive interaction compared to those who spread real news, resulting in the formation of a denser community.

Molecular representation learning is pivotal in predicting molecular properties and advancing drug design. Traditional methodologies, which predominantly rely on homogeneous graph encoding, are limited by their inability to integrate external knowledge and represent molecular structures across different levels of granularity. To address these limitations, we propose a paradigm shift by encoding molecular graphs into heterogeneous structures, introducing a novel framework: Knowledge-aware Contrastive Heterogeneous Molecular Graph Learning. This approach leverages contrastive learning to enrich molecular representations with embedded external knowledge. KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism. This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction prediction. Extensive benchmarking demonstrates KCHML's superiority over state-of-the-art molecular property prediction models, underscoring its ability to capture intricate molecular features.

Session-based recommendations have become increasingly important in social media platforms due to the dynamic and temporal nature of user interactions. The utilization of Graph Neural Networks in these systems has grown due to their proficiency in incorporating node information and structural topology. However, current recommendation methods that use graphs focus on recommendations within a single session, neglecting the more complex dependencies between different sessions. This omission limits improvements in the accuracy of recommendations. In addition, existing GNN-based approaches generally focus on simple binary connections, neglecting to capture the intricate and heterogeneous interactions in real-world situations. Furthermore, a notable obstacle arises from the absence of node positional information for hyperedges in hypergraphs. Therefore, different item orders can lead to identical hyperedges, which limits the formation of precise session vector representations. The paper proposes a unified framework utilizing heterogeneous hypergraph neural networks for session-based social recommendations to address these limitations. This framework utilizes hypergraphs to depict complex multivariate connections among sessions, social networks, and items. It addresses the problem of hyperedge ambiguity while maintaining the sequential order of data. The methodology entails creating a linkage graph and a session-item graph, which aid in identifying similar user intentions across various sessions and potential behavior patterns within a single session. In addition, the framework utilizes a Graph Attention Network (GAT) to combine social information from users and their connections, thereby improving the representation of user interests. Empirical assessments on three datasets show that our proposed model outperforms popular recommendation models. This emphasizes its effectiveness in accurately capturing user preferences and behaviors in session-based social recommendations.

Transformers-based trackers offer significant potential for integrating semantic interdependence between template and search features in tracking tasks. Transformers possess inherent capabilities for processing long sequences and extracting correlations within them. Several researchers have explored the feasibility of incorporating Transformers to model continuously changing search areas in tracking tasks. However, their approach has substantially increased the computational cost of an already resource-intensive Transformer. Additionally, existing Transformers-based trackers rely solely on mechanically employing multi-head attention to obtain representations in different subspaces, without any inherent bias. To address these challenges, we propose HEART (Historical Information Embedding And Subspace Re-weighting Tracker). Our method embeds historical information into the queries in a lightweight and Markovian manner to extract discriminative attention maps for robust tracking. Furthermore, we develop a multi-head attention distribution mechanism to retrieve the most promising subspace weights for tracking tasks. HEART has demonstrated its effectiveness on five datasets, including OTB-100, LaSOT, UAV123, TrackingNet, and GOT-10k.

Social events reflect the dynamics of society and, here, natural disasters and emergencies receive significant attention. The timely detection of these events can provide organisations and individuals with valuable information to reduce or avoid losses. However, due to the complex heterogeneities of the content and structure of social media, existing models can only learn limited information; large amounts of semantic and structural information are ignored. In addition, due to high labour costs, it is rare for social media datasets to include high-quality labels, which also makes it challenging for models to learn information from social media. In this study, we propose two hyperbolic graph representation-based methods for detecting social events from heterogeneous social media environments. For cases where a dataset has labels, we design aHyperbolicSocialEventDetection (HSED) model that converts complex social information into a unified social message graph. This model addresses the heterogeneity of social media, and, with this graph, the information in social media can be used to capture structural information based on the properties of hyperbolic space. For cases where the dataset is unlabelled, we design anUnsupervisedHyperbolicSocialEventDetection (UHSED). This model is based on the HSED model but includes graph contrastive learning to make it work in unlabelled scenarios. Extensive experiments demonstrate the superiority of the proposed approaches.

The dynamic and temporal nature of user interactions on social media platforms has increased the importance of session-based recommendations. The adoption of graph neural networks in these systems has increased due to their capacity to incorporate structural topology and node information. Nevertheless, current session-based recommendation methods relying on pairwise graph structure ignore intricate and evolving interactions between users, items, and sessions across domains. However, most methodologies focus on a scenario where consumers interact with a single domain. As a result, they cannot accurately represent the intricate and evolving correlations between users and items in cross-domain scenarios. They consistently face insufficient data because they overlook the fact that users’ behaviors are distributed across domains and sessions. To address these challenges, we propose a novel dynamic hypergraph-based framework for cross-domain session-based social recommendations (DHCSRs). We construct a dynamic heterogeneous hypergraph to model the intricate higher order correlations among inter- and intradomain sessions, items, users, and social networks. In intradomain sessions, the hyperedge incorporates domain-specific features into the embedding process for user embedding by considering product categories. Interdomain sessions capture the complex interests of users who engage with diverse types of content. In addition, the framework utilizes gated recurrent units for user behavior and a domain-driven session-based RNN to capture user and session representations. The domain-driven session-based RNN exchanges information across sessions from various domains in sequential order to ensure alignment of domain interactions. The user behavior RNN learns the user’s global interests and captures behavioral differences across domains. Finally, user behavioral information and session representations are aggregated with the session and item representations from the hypergraph to predict user behavior. Comprehensive experiments demonstrate that the DHCSR model outperforms several baselines across all four datasets, with improvements ranging from 3.56% to 18.31% in HR and from 5.08% to 25.65% in NDCG, significantly enhancing the accuracy of recommendations.

The widespread diffusion of fake news has become a critical problem on dynamic social media worldwide, which requires effective strategies for fake news detection to alleviate its hazardous consequences for society. However, most recent efforts only focus on the features of news content and social context without realizing the benefits of large language models (LLMs) and multiple knowledge graphs (KGs), thus failing to improve detection capabilities further. To tackle this issue, we present a multiknowledge and LLM-inspired heterogeneous graph neural network for fake news detection (MiLk-FD), by combining KGs, LLMs, and graph neural networks (GNNs). Specifically, we first model news content as a heterogeneous graph (HG) containing news, entity, and topic nodes and then fuse the knowledge from three KGs to augment the factual basis of news articles. Meanwhile, we leverage TransE to initialize the knowledge features and employ LLaMa2-7B to obtain the initial feature vectors of news articles. After that, we utilize the devised HG transformer to learn news embeddings with specific feature distribution in high-dimensional spaces by aggregating neighborhood information according to metapaths. Finally, a classifier based on multilayer perceptron (MLP) is trained to predict each news article as fake or true. Through experiments, we demonstrate that our proposed framework surpasses ten baselines according to accuracy, precision, F1-score, recall, and ROC in four public real-world benchmarks (i.e., COVID-19, FakeNewsNet, PAN2020, Liar).

Graph Convolutional Networks (GCNs) are currently the most widely used method for processing graph-structured data. However, recent research has revealed that the performance of GCNs dramatically decreases when confronted with adversarial attacks. This severely hinders their application in security-critical domains. Therefore, the development of GCNs that are resilient to adversarial attacks has emerged as a prominent research focus. Despite this, most current defense models with complex network architectures and optimization objectives are typically designed based on specific feature assumptions or attack manifestations, and do not enhance the inherent robustness of GCNs. They also overlook the changes induced by perturbations of varying intensities and the difference in attack phenomenon across different datasets. In response to this, we have delved into the impact of adversarial attacks on the spectrum, and propose an effective adaptive robust spectrum filter GCN (ASF-GCN). This approach enhances the robustness of GCN models through adaptive filtering without introducing additional conditional assumptions. We theoretically analyze that graphs have different robust frequency intervals under different conditions, validating the necessity of adaptive filtering. Additionally, we elucidate the role of degree distribution and maximum eigenvalue in adaptation. Extensive experiments on real-world graphs reveal that our model surpasses other defense models in overall performance.

Knowledge Graphs (KGs) often suffer from incompleteness and this issue motivates the task of Knowledge Graph Completion (KGC). Traditional KGC models mainly concentrate on static KGs with a fixed set of entities and relations, or dynamic KGs with temporal characteristics, faltering in their generalization to constantly evolving KGs with possible irregular entity drift. Thus, in this paper, we propose a novel link prediction model based on the embedding representation to handle the incompleteness of KGs with entity drift, termed as DCEL. Unlike traditional link prediction, DCEL could generate precise embeddings for drifted entity without imposing any regular temporal characteristic. The drifted entity is added into the KG with its links to the existing entity predicted in an incremental fashion with no requirement to retrain the whole KG for computational efficiency. In terms of DCEL model, it fully takes advantages of unstructured textual description, and is composed of four modules, namely MRC (Machine Reading Comprehension), RCAA (Relation Constraint Attentive Aggregator), RSA (Relation Specific Alignment) and RCEO (Relation Constraint Embedding Optimization). Specifically, the MRC module is first employed to extract short texts from long and redundant descriptions. Then, RCAA is used to aggregate the embeddings of textual description of drifted entity and the pre-trained word embeddings learned from corpus to a single text-based entity embedding while shielding the impact of noise and irrelevant information. After that, RSA is applied to align the text-based entity embedding to graph-based space to obtain the corresponding graph-based entity embedding, and then the learned embeddings are fed into the gate structure to be optimized based on the RCEO to improve the accuracy of representation learning. Finally, the graph-based model TransE is used to perform link prediction for drifted entity. Extensive experiments conducted on benchmark datasets in terms of evaluation protocols of MRR and Hits@ \(k\) reveal the superiority of DCEL model compared to its SOTAs.

The problem of infection source detection deals with localizing the infection source in a given network. While the problem has been extensively studied in the past, researchers have mainly focused on simulated infection networks which may not be the correct reflection of the dynamics of real-world infections. More significantly, the existing methods assume that a rumor source lies at the center of an infection network (source-centrality), which is not always true in sparse real-world rumor networks. Due to the randomness of infection flow in such networks, the source may lie away from the center (source-skewness). There is also a lack of real-world infection network datasets to provide a true real-world perspective. Therefore, we revisit the source detection problem and contemplate a shift from mainstream simulations to a real-world paradigm. To this end, we generate two novel rumor network datasets, Cov19-RN and Use20-RN, based on COVID-19 and US Elections 2020 misinformation trends on Twitter (currently$\mathbb {X}$). Besides, inspired by the technicalities inherent to real-world rumor networks, we propose a real-world oriented algorithm called Generalized Exoneration and Prominence based Age, GEPA, for rumor source detection. GEPA addresses the problem of source-skewness to detect rumor sources using the concept of generalized local prominence, which we introduce in this study. Our experiments show that GEPA significantly outperforms the state-of-the-art methods, producing detection rates of 73.6% against 61.5% of the closest competing method on Cov19-RN, and 61.5% against 52.6% of the closest competing method on Use20-RN. To the best of our knowledge, this study is the first such work to deal with source detection in real-world rumor networks and address the problem of source-skewness. Our complete source code, benchmark datasets and detailed results are available athttps://github.com/tesla121/GEPA.

The excellent performance of graph neural networks (GNNs), which learn node representations by aggregating their neighborhood information, led to their use in various graph tasks. However, GNNs are black box models, the prediction results of which are difficult to understand directly. Although node attributes are vital for making predictions, previous studies have ignored their importance for explanation. This study presents GAFExplainer, a novel GNN explainer that emphasizes node attributes via attribute augmentation and fusion embedding. The former enhances node attribute encoding for more expressive masks, while the latter preserves the discrimination of node representations across different layers. Together, these modules significantly improve explanation performance. By training the explanatory network, a global view explanation of GNN models is obtained, and reasonably explainable subgraphs are available for new graphs, thus rendering the model well-generalizable. Multiple sets of experimental results on real and synthetic datasets demonstrate that the proposed model provides valid and accurate explanations. In the visual analysis, the explanations obtained by the proposed model are more comprehensible than those in existing work. Further, the fidelity evaluation and efficiency comparison reveal that with an average performance improvement of 8.9$\% $compared with representative baselines, GAFExplainer achieves the best fidelity metrics while maintaining computational efficiency.

Anomalies often occur in real-world information networks/graphs, such as malevolent users in online review networks and fake news in social media. When representing such structured network data as graphs, anomalies usually appear as anomalous nodes that exhibit significantly deviated structure patterns, or different attributes, or the both. To date, numerous unsupervised methods have been developed to detect anomalies based on residual analysis, which assumes that anomalies will introduce larger residual errors (i.e., graph reconstruction loss). While these existing works achieved encouraging performance, in this paper, we formally prove that their employed learning objectives, i.e., MSE and cross-entropy losses, encounter significant limitations in learning the major data distributions, particularly for anomaly detection, and through our preliminary study, we reveal that the vanilla residual analysis-based methods cannot effectively investigate the rich graph structure. Upon these discoveries, we propose a novel structure-biased graph anomaly detection framework (SALAD) to attain anomalies’ divergent patterns with the assistance of a specially designed node representation augmentation approach. We further present two effective training objectives to empower SALAD to effectively capture the major structure and attribute distributions by emphasizing less on anomalies that introduce higher reconstruction errors under the encoder-decoder framework. The detection performance on eight widely-used datasets demonstrates SALAD's superiority over twelve state-of-the-art baselines. Additional ablation and case studies validate that our data augmentation method and training objectives result in the impressive performance.

Multi-scenario and multi-task recommendation systems efficiently facilitate knowledge transfer across different scenarios and tasks. However, many existing approaches inadequately incorporate personalized information across users and scenarios. Moreover, the conversion rate (CVR) task in multi-task learning often encounters challenges like sample selection bias, resulting from systematic differences between the training and inference sample spaces, and data sparsity due to infrequent clicks. To address these issues, we propose Adaptive Entire-space Multi-scenario Multi-task Transfer Learning model (AEM$^{2}$TL) with four key modules: 1) Scenario-CGC (Scenario-Customized Gate Control), 2) Task-CGC (Task-Customized Gate Control), 3) Personalized Gating Network, and 4) Entire-space Supervised Multi-Task Module. AEM$^{2}$TL employs a multi-gate mechanism to effectively integrate shared and specific information across scenarios and tasks, enhancing prediction adaptability. To further improve task-specific personalization, it incorporates personalized prior features and applies a gating mechanism that dynamically scales the top-layer neural units. A novel post-impression behavior decomposition technique is designed to leverage all impression samples across the entire space, mitigating sample selection bias and data sparsity. Furthermore, an adaptive weighting mechanism dynamically allocates attention to tasks based on their relative importance, ensuring optimal task prioritization. Extensive experiments on one industrial and two real-world public datasets indicate the superiority of AEM$^{2}$TL over state-of-the-art methods.

Semi-supervised clustering leverages prior information in the form of constraints to achieve higher-quality clustering outcomes. However, most existing methods struggle with large-scale datasets owing to their high time and space complexity. Moreover, they encounter the challenge of seamlessly integrating various constraints, thereby limiting their applicability. In this paper, we presentScalableSemi-supervised clustering viaStructuralEntropy (SSSE), a novel method that tackles scalable datasets with different types of constraints from diverse sources to perform both semi-supervised partitioning and hierarchical clustering, which is fully explainable compared to deep learning-based methods. Specifically, we design objectives based on structural entropy, integrating constraints for semi-supervised partitioning and hierarchical clustering. To achieve scalability on data size, we develop efficient algorithms based on graph sampling to reduce the time and space complexity. To achieve generalization on constraint types, we formulate a uniform view for widely used pairwise and label constraints. Extensive experiments on real-world clustering datasets at different scales demonstrate the superiority of SSSE in clustering accuracy and scalability with different constraints. Additionally, Cell clustering experiments on single-cell RNA-seq datasets demonstrate the functionality of SSSE for biological data analysis.

Many supervised learning-based facial expression recognition (FER) methods achieve good performance with the assistance of expression labels and a complex framework. However, there are inconsistent annotations in different expression datasets, making the above methods disadvantageous for new expression datasets or datasets with limited training data. The objective of this paper is to learn self-supervised facial expression features that enable the FER model not to rely on the annotation consistency of the different datasets. Most current self-supervised learning algorithms based on contrastive learning learn the representation by forcing different augmented views of the same image close in the embedding space, but they cannot cover all variances within a semantic class. We propose a heatmap neighbor contrastive learning (HNCL) method for FER. It treats the images corresponding to the heatmap nearest neighbors of expressions as other positives, providing more semantic variations than pre-defined augmented transformations. Therefore, our HNCL can learn better expression features covering more intra-class variances, improving the performance of the FER model based on self-supervised learning. After fine-tuning, HNCL with a simple framework achieves top-three performance on the in-the-lab datasets and even matches the performance of state-of-the-art supervised learning methods on the in-the-wild datasets.

Multivariate time series anomaly detection has shown potential in various fields, such as finance, aerospace, and security. The fuzzy definition of data anomalies, the complexity of data patterns, and the scarcity of abnormal data samples pose significant challenges to anomaly detection. Researchers have extensively employed autoencoders (AEs) and generative adversarial networks (GANs) in studying time series anomaly detection methods. However, relying on reconstruction error, the AE-based anomaly detection algorithm needs more effective regularization methods, rendering it susceptible to the problem of overfitting. Meanwhile, GAN-based anomaly detection algorithms require high-quality training data, significantly impacting their practical deployment. We propose a novel GAN based on a dual-discriminator structure to address these issues. The model first processes the data with the generator to obtain the reconstruction error and then calculates pseudo-labels to divide the data into two categories. One data category is input into the first discriminator, where a minor loss between the data and its reconstructed counterpart is better. The other data category is input into the second discriminator, where a larger loss between the data and its reconstructed counterpart is better. Through this process, the model can effectively constrain the generator, retaining information on normal data during data reconstruction while discarding information on abnormal data. After conducting experiments on multiple benchmark datasets, the proposed GAN based on a dual-discriminator structure achieved good results in anomaly detection, outperforming several advanced methods. Additionally, the model also performed well in practical transformer data.

In this article, we propose a new graph neural network (GNN) explainability model, CiRLExplainer, which elucidates GNN predictions from a causal attribution perspective. Initially, a causal graph is constructed to analyze the causal relationships between the graph structure and GNN predicted values, identifying node attributes as confounding factors between the two. Subsequently, a backdoor adjustment strategy is employed to circumvent these confounders. Additionally, since the edges within the graph structure are not independent, reinforcement learning is incorporated. Through a sequential selection process, each step evaluates the combined effects of an edge and the previous structure to generate an explanatory subgraph. Specifically, a policy network predicts the probability of each candidate edge being selected and adds a new edge through sampling. The causal effect of this action is quantified as a reward, reflecting the interactivity among edges. By maximizing the policy gradient during training, the reward stream of the edge sequence is optimized. The CiRLExplainer is versatile and can be applied to any GNN model. A series of experiments was conducted, including accuracy (ACC) analysis of the explanation results, visualization of the explanatory subgraph, and ablation studies considering node attributes as confounding factors. The experimental results demonstrate that our model not only outperforms current state-of-the-art explanation techniques, but also provides precise semantic explanations from a causal perspective. Additionally, the experiments validate the rationale for considering node attributes as confounding factors, thereby enhancing the explanatory power and ACC of the model. Notably, across different datasets, our explainer achieved improvements over the best baseline models in the ACC-area under the curve (AUC) metrics by 5.89%, 5.69%, and 4.87%, respectively.

The human brain is a highly complex neurological system that has been the subject of continuous exploration by scientists. With the help of modern neuroimaging techniques, there has been significant progress made in brain disorder analysis. There is an increasing interest about utilizing artificial intelligence techniques to improve the efficiency of disorder diagnosis in recent years. However, these methods rely only on neuroimaging data for disorder diagnosis and do not explore the pathogenic mechanism behind the disorder or provide an interpretable result toward the diagnosis decision. Furthermore, the scarcity of medical data limits the performance of existing methods. As the hot application of graph neural networks (GNNs) in molecular graphs and drug discovery due to its strong graph-structured data learning ability, whether GNNs can also play a huge role in the field of brain disorder analysis. Thus, in this work, we innovatively model brain neuroimaging data into graph-structured data and propose knowledge distillation (KD) guided brain subgraph neural networks to extract discriminative subgraphs between patient and healthy brain graphs to explain which brain regions and abnormal functional connectivities cause the disorder. Specifically, we introduce the KD technique to transfer the knowledge of pretrained teacher model to guide brain subgraph neural networks training and alleviate the problem of insufficient training data. And these discriminative subgraphs are conducive to learn better brain graph-level representations for disorder prediction. We conduct abundant experiments on two functional magnetic resonance imaging datasets, i.e., Parkinson's disease (PD) and attention-deficit/hyperactivity disorder (ADHD), and experimental results well demonstrate the superiority of our method over other brain graph analysis methods for disorder prediction accuracy. The interpretable experimental results given by our method are consistent with corresponding medical research, which is encouraging to provide a potential for deeper brain disorder study.

Graph neural networks (GNNs) have shown promise in graph classification tasks, but they struggle to identify out-of-distribution (OOD) graphs often encountered in real-world scenarios, posing a significant obstacle for their open-world deployment. Due to the unpredictable nature of the various distributions to which OOD graphs adhere, the challenge of OOD graph detection lies in enabling models to capture distribution differences between in-distribution (ID) and OOD graphs. Current methods often introduce a subset of OOD patterns, such as synthetic OOD graphs, to facilitate learning the discrimination between ID and OOD graphs. However, these OOD patterns may not sufficiently encapsulate the entire range of OOD graphs, leading to inadequate learning of the distribution differences between ID and OOD graphs. In this article, we propose a novel OOD graph detection algorithm, ODGNN. The ODGNN does not expose GNNs to any OOD patterns during model training, thus reducing bias toward specific types of OOD graph samples and enhancing OOD graph detection. The algorithm differentiates graphs by evaluating whether the input graphs conform to established ID graph class-conditioned distributions. Specifically, during model training, the ODGNN integrates a Gaussian encoder into GNNs to characterize ID graph classes using distinct class-conditioned distributions. During inference, OOD graphs are mapped to a representation space distant from ID graphs due to their divergence from any known class-conditioned distribution. Extensive experiments conducted on real-world datasets validate the effectiveness of the ODGNN in enhancing OOD detection performance across various GNN-based graph classification models. The ODGNN also demonstrates superior performance compared to state-of-the-art OOD graph detection competitors.

Multiple instance learning (MIL) trains models from bags of instances, where each bag contains multiple instances, and only bag-level labels are available for supervision. The application of graph neural networks (GNNs) in capturing intrabag topology effectively improves MIL. Existing GNNs usually require filtering low-confidence edges among instances and adapting graph neural architectures to new bag structures. However, such asynchronous adjustments to structure and architecture are tedious and ignore their correlations. To tackle these issues, we propose a reinforced GNN framework for MIL (RGMIL), pioneering the exploitation of multiagent deep reinforcement learning (MADRL) in MIL tasks. MADRL enables the flexible definition or extension of factors that influence bag graphs or GNNs and provides synchronous control over them. Moreover, MADRL explores structure-to-architecture correlations while automating adjustments. Experimental results on multiple MIL datasets demonstrate that RGMIL achieves the best performance with excellent explainability. The code and data are available at https://github.com/RingBDStack/RGMIL.

Multi-Behavior Recommendation (MBR) aims to model personalized user preferences by integrating diverse interaction behaviors (e.g., page view, favorite, add to cart, purchase). However, latent confounders such as contextual influences and social relationships can obscure the true causal effects in real-world scenarios, thereby confounding the model’s prediction. Although existing MBR research extensively explores behavioral dependencies and heterogeneity, it frequently overlooks the impact of latent confounders, thereby limiting its ability to capture users’ genuine preferences. To address the limitations of existing methods, we identify two key challenges in MBR: (1) how to infer latent confounders, and (2) how to mitigate their influence across multi-behavior interactions. To this end, we propose Causal Variational Inference for Deconfounded (CVID) MBR. CVID employs a variational graph autoencoder to model latent uncertainty in multi-behavior interactions and introduces a confounder inference module to generate behavior-specific latent confounders via variational inference. In the conditional diffusion module, noise is progressively injected during the forward process to simulate the dynamic evolution of user preferences, while the reverse process leverages the inferred latent confounders to guide denoising through back-door adjustment, thereby recovering the true causal effects between multi-behavior interactions and the model’s prediction. Extensive experiments on public multi-behavior datasets demonstrate that CVID consistently outperforms state-of-the-art baselines in mitigating confounding effects and improving recommendation accuracy, validating its effectiveness and superiority.

Graph neural networks (GNNs) have been used extensively as a backbone for social recommendation. However, their application to a diverse range of situations is still rather limited. This is because graph structures only leverage pairwise user relationships. They cannot capture the higher-order relationships so common in the real world, and ignoring the interest friends and strangers might have in similar items is severely hampering the expressiveness of the current graph-based recommendation models. Hence, in this article, we outline a heterogeneous hypergraph neural network for social recommendation, called Heterogeneous Hypergraph neural network for Social Recommendation using an Attention Network (HHGSA), that incorporates an attention network to address these issues. The hypergraph is able to represent higher-order relationships through five motifs: friend and stranger item appeal, item similarity, user similarity based on interactions with items, and social relations. Two modules, the attentive vertex aggregation module and the attentive hyperedge aggregation module, capture user and item attention. In addition, it has been discovered that similar items have identical appeal when displayed to users. A GNN aggregates the user embedding data, including information about the friend and stranger and item embeddings. Finally, information about users and items is aggregated for social recommendations. Extensive experiments on four datasets demonstrate that the HHGSA model outperforms a wide range of baselines and can significantly improve the accuracy of recommendations.

Large language models (LLMs) have emerged as valuable tools for enhancing textual features in various text-related tasks.Despite their superiority in capturing the lexical semantics between tokens for text analysis, our preliminary study on two popular LLMs, i.e., GPT-3.5 and Llama2, shows that simply applying news embeddings from LLMs is ineffective for fake news detection.Such embeddings only encapsulate the language styles between tokens.Meanwhile, the high-level semantics among named entities and topics, which reveal the deviating patterns of fake news, have been ignored.Therefore, we propose a topic model together with a set of specially designed prompts to extract topics and real entities from LLMs and model the relations among news, entities, and topics as a heterogeneous graph to facilitate investigating news semantics.We then propose a Generalized Page-Rank model and a consistent learning criterion for mining the local and global semantics centered on each news piece through the adaptive propagation of features across the graph.Our model shows superior performance on five benchmark datasets over seven baseline methods and the efficacy of the key ingredients has been thoroughly validated.1. https://api.openai.

LiDAR is a key sensor for accurately sensing of the environment in autonomous driving. While existing 3D object detection methods generally rely on data augmentation and feature fusion to improve performance, the challenge of dealing with sample imbalance is often overlooked. We design a novel 3D detection network, IFNet, that tackles these issues by introducing mutually reinforcing data augmentation and feature enhancement strategies. It aims to achieve a dual purpose: 1) correcting the category imbalance by directly enhancing pedestrian samples using mixed data augmentation, i.e., RG-Aug; and 2) enhancing feature perception by introducing the decoupling and attention fusion module (DAF). DAF enables robust feature representations across different layers, improving the detection performance, especially for small objects in the scene. Comprehensive experiments on the KITTI dataset and comparisons with state-of-the-art methods demonstrate the superiority of our proposed approach.

Deep learning is increasingly crucial in scientific discovery, accelerating research in various fields. Exploring brain science using deep learning has garnered significant interest, particularly in the recognition of brain disorders. However, existing methods face limitations in the discriminability of learned brain graph representations and the identification of neurological biomarkers associated with brain disorders. Moreover, the lack of model explainability leads to suboptimal brain graph analysis. To address these challenges, we propose a bi-level brain graph contrastive learning framework with an interpretable learning kernel for brain disorder analysis. Our framework diverges from traditional graph contrastive learning methods by augmenting meaningful brain graphs using the counterfactual thinking-based mechanism, ensuring reliable graph generation that preserves discriminative information. Secondly, we introduce bi-level contrastive loss with intra-and inter-class contrasts to enhance the brain graph representation learning. Most importantly, we design an interpretable brain graph learning kernel to highlight critical regions and connections, thereby facilitating the discovery of potential neurological biomarkers associated with brain disorders in subsequent analysis. The effectiveness of our method11https://githuh.com/JustinGie/Cf-BCL in brain graph representation learning and discriminative substructure detection is demonstrated through the evaluation of disorder prediction and pathogenic analysis on three real-world brain disorder datasets. Moreover, our framework may provide novel insights into brain science based on the results of comparison with medical research.

Graph-based fraud detection has attracted increasing attention in recent years, reflecting its growing potential in mitigating sophisticated fraudulent activities. The main objective of graph-based fraud detection is to discern between fraud-sters and normal entities within graphs. As fraudsters adopt increasingly sophisticated camouflage tactics, combating them has become an urgent task. Despite the complex interactions within real-world networks involving high-order relations, ex-isting graph-based fraud detection methods often neglect non-pairwise relationships among entities in graphs. Thus, we empha-size the significance of investigating beyond pairwise relationships for building an effective fraud detection model. In this paper, we propose constructing a hypergraph from the original input graph to encapsulate comprehensive high-order relations and present TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng for detecting CAmouflaged maLicious actors in online social networks. TROPICAL learns representations by processing different hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. Subsequently, the model feeds the learned aggregated sequential information into the transformer encoder, achieving rich rep-resentations for effective camouflaged fraudster detection. The superiority of TROPICAL is demonstrated through experiments conducted on two real-world datasets, compared against the state-of-the-art fraud detection models. The source codes and datasets of our work are available at https://github.comNenusHaghighi/TROPICAL.

Since the inception of online fake news detection, the technique of natural language processing has predominantly been leading the field by utilizing text classification to discern veracity. From the network perspective, news traveling within a social network typically exhibits non-textual correlations aligned with the network of news propagation or news-user interaction. Therefore, with the advancement of graph learning, there have been emerging approaches incorporating graphs of social contexts as auxiliary information, of which the performance still relies on learning semantics from news text. As fake news becomes more adept at employing the writing pattern of real news and the assessment of certain news contents requires domain-specific knowledge, distinguishing real news from fake ones based on the text has become increasingly challenging. This raises a question: Can we debunk fake news without going through the text? Thus, this work aims to explore the feasibility of differentiating between real and fake news by capturing its relationships with other news and people in the network. We propose a method named ComE-DeFake which extracts intricate relations beyond pairwise of news and users in social contexts to detect fake news. Experimental results reveal that our method without using news text outperforms all baseline methods. This suggests that, if high-order complicated relations are fully captured, it is achievable to debunk fake news without analyzing its text.

Big Data has various formats, substandard data models, and diverse semantics. Understanding this vast, continuous, and constantly evolving data is challenging and requires sophisticated data science pipelines that not only turn the raw data into contextual knowledge and insights but also generate meaningful and personalized narratives to facilitate the understanding and interpretation of the Big Data. Existing methods often fail to provide the necessary context and personalization to make data actionable to diverse stakeholders. To achieve this goal, we introduce the Open Story Model (OSM), a novel data science pipeline that: i) transforms the unprocessed data into a structured Knowledge Graph based on a unified graph data model of typed nodes and edges; ii) generates meaningful narratives on top of the Knowledge Graph; and (iii) link narratives to construct personalized stories for various stakeholders based on their goals. We model each story as an interactive data product to allow stakeholders to engage with and manipulate data in real-time to explore, analyze, and visualize the information in ways that suit their specific needs and questions. To demonstrate the practical application and efficacy of the OSM framework, we focus on a use case in the health domain and explore how OSM facilitates the detection and prediction of cancer by transforming the data into personalized stories for various stakeholders.

Anomalous node detection in a static graph faces significant challenges due to the rarity of anomalies and the substantial cost of labeling their deviant structure and attribute patterns. These challenges give rise to data-centric problems, including extremely imbalanced data distributions and intricate graph learning, which significantly impede machine learning and deep learning methods from discerning the patterns of graph anomalies with few labels. While these issues remain crucial, much of the current research focuses on addressing the induced technical challenges, treating the shortage of labeled data as a given. Distinct from previous efforts, this work focuses on tackling the data-centric problems by generating auxiliary training nodes that conform to the original graph topology and attribute distribution. We categorize this approach as data-centric, aiming to enhance existing anomaly detectors by training them on our synthetic data. However, the methods for generating nodes and the effectiveness of utilizing synthetic data for graph anomaly detection remain unexplored in the realm. To answer these questions, we thoroughly investigate the denoising diffusion model. Drawing from our observations on the diffusion process, we illuminate the shifts in graph energy distribution and establish two principles for designing denoising neural networks tailored to graph anomaly generation. From the insights, we propose a diffusion-based graph generation method to synthesize training nodes, which can be promptly integrated to work with existing anomaly detectors. The empirical results on eight widely-used datasets demonstrate our generated data can effectively enhance the nine state-of-the-art graph detectors' performance.

In this paper, we propose an interpretable brain graph contrastive learning framework, which aims to learn brain graph representations by a unsupervised way for disorder prediction and pathogenic analysis. Our framework consists of two key designs: We first utilize the controllable data augmentation strategy to perturb unimportant structures and attribute features for the generation of brain graphs. Then, considering that the difference of healthy and patient brain graphs is small, we introduce hard negative sample evaluation to weight negative samples of the contrastive loss, which can learn more discriminative brain graph representations. More importantly, our method can observe salient brain regions and connections for pathogenic analysis. We conduct disorder prediction and interpretable analysis experiments on three real-world neuroimaging datasets to demonstrate the effectiveness of our framework.

Social events reflect changes in communities, such as natural disasters and emergencies. Detection of these situations can help residents and organizations in the community avoid danger and reduce losses. The complex nature of social messages makes social event detection on social media challenging. The challenges that have a greater impact on social media detection models are as follows: (1) the amount of social media data is huge but its availability is small; (2) social media data is a tree structure and traditional Euclidean space embedding will distort embedded features; and (3) the heterogeneity of social media networks makes existing models unable to capture rich information well. To solve the above challenges, we propose a Heterogeneous Information Graph representation via Hyperbolic space combined with an Automatic Meta-path selection (GraphHAM) model, an efficient framework that automatically selects the meta-path's weight and combines hyperbolic space to learn information on social media. In particular, we apply an efficient automatic meta-path selection technique and convert the selected meta-path into a vector, thereby reducing the requisite amount of labeled data for the model. We also design a novel Hyperbolic Multi-Layer Perceptron (HMLP) to further learn the semantic and structural information of social information. Extensive experiments show that GraphHAM can achieve outstanding performance on real-world data using only 20% of the whole dataset as the training set. Our code can be found on GitHub https://github.com/ZITAIQIU/GraphHAM.

Fake news is pervasive on social media, inflicting substantial harm on public discourse and societal well-being. We investigate the explicit structural information and textual features of news pieces by constructing a heterogeneous graph concerning the relations among news topics, entities, and content. Through our study, we reveal that fake news can be effectively detected in terms of the atypical heterogeneous subgraphs centered on them, which encapsulate the essential semantics and intricate relations between news elements. However, suffering from the heterogeneity, exploring such heterogeneous subgraphs remains an open problem. To bridge the gap, this work proposes a heterogeneous subgraph transformer HeteroSGT to exploit subgraphs in our constructed heterogeneous graph. In HeteroSGT, we first employ a pre-trained language model to derive both word-level and sentence-level semantics. Then the random walk with restart (RWR) is applied to extract subgraphs centered on each news, which are further fed to our proposed subgraph Transformer to quantify the authenticity. Extensive experiments on five real-world datasets demonstrate the superior performance of HeteroSGT over five baselines. Further case and ablation studies validate our motivation and demonstrate that performance improvement stems from our specially designed components.

Modeling users’ short-term dynamic and long-term static interests to enhance Point-of-Interests (POI) recommendation performance has shown lots of advantages. Since users’ check-in records can be viewed as a graph network, methods based on Graph Neural Networks (GNNs) have recently shown promising applicability for POI recommendation. However, existing GNN-based works have the following shortcomings: (1) ignoring the impact of complex higher-order relationships between user-POI dynamics over time; and (2) ignoring the difference in POI importance that cannot effectively capture the imbalances of geographical influence among POIs. To address these challenges, we propose a novel Self-supervised Long-and Short-term model (SLS-REC) for POI recommendation. Specifically, we first design a spatio-temporal Hawkes attention hypergraph neural network to capture the spatial dependence and temporal evolution in users’ short-term dynamic interests. Then we introduce a dynamic propagation mechanism of GNNs to learn the geographic influences underlying geographic imbalances among POIs. In addition, the contrastive learning framework over a fine-grained node dropout strategy is applied to maximize the mutual information of long and short-term interest representations. Finally, we adaptively unify the recommendation and self-supervised task with an attention-based mechanism to optimize the proposed SLS-REC model for POI recommendation. Experiments on real-world datasets show that the proposed model significantly outperforms state-of-the-art methods.

Learning the representation of sentences is fundamental work in the field of Natural Language Processing. Although BERT-like transformers have achieved new SOTAs for sentence embedding in many tasks, they have been proven difficult to capture semantic similarity without proper fine-tuning. A common idea to measure Semantic Textual Similarity (STS) is considering the distance between two text embeddings defined by the dot product or cosine function. However, the semantic embedding spaces induced by pretrained transformers are generally non-smooth and tend to deviate from a normal distribution, which makes traditional distance metrics imprecise. In this paper, we first empirically explain the failure of cosine similarity in semantic textual similarity measuring, and present CoSENT, a novelConsistentSENTence embedding framework. Concretely, a supervised objective function is designed to optimize the Siamese BERT network by exploiting ranked similarity labels of sample pairs. The loss function utilizes uniform cosine similarity-based optimization for both the training and prediction phases, improving the consistency of the learned semantic space. Additionally, the unified objective function can be adaptively applied to different datasets with various types of annotations and different comparison schemes of the STS tasks only by using sortable labels. Empirical evaluations on 14 common textual similarity benchmarks demonstrate that the proposed CoSENT excels in performance and reduces training time cost.

Analysis of neuroimaging data (e.g., Magnetic Resonance Imaging, structural and functional MRI) plays an important role in monitoring brain dynamics and probing brain structures. Neuroimaging data are multi-featured and non-linear by nature, and it is a natural way to organise these data as tensors prior to performing automated analyses such as discrimination of neurological disorders like Parkinson's Disease (PD) and Attention Deficit and Hyperactivity Disorder (ADHD). However, the existing approaches are often subject to performance bottlenecks (e.g., conventional feature extraction and deep learning based feature construction), as these can lose the structural information that correlates multiple data dimensions or/and demands excessive empirical and application-specific settings. This study proposes a Deep Factor Learning model on a Hilbert Basis tensor (namely, HB-DFL) to automatically derive latent low-dimensional and concise factors of tensors. This is achieved through the application of multiple Convolutional Neural Networks (CNNs) in a non-linear manner along all possible dimensions with no assumed a priori knowledge. HB-DFL leverages the Hilbert basis tensor to enhance the stability of the solution by regularizing the core tensor to allow any component in a certain domain to interact with any component in the other dimensions. The final multi-domain features are handled through another multi-branch CNN to achieve reliable classification, exemplified here using MRI discrimination as a typical case. A case study of MRI discrimination has been performed on public MRI datasets for discrimination of PD and ADHD. Results indicate that 1) HB-DFL outperforms the counterparts in terms of FIT, mSIR and stability (mSC and umSC) of factor learning; 2) HB-DFL identifies PD and ADHD with an accuracy significantly higher than state-of-the-art methods do. Overall, HB-DFL has significant potentials for neuroimaging data analysis applications with its stability of automatic construction of structural features.

Oriented object detection has garnered significant attention. However, rotational symmetry and discontinuity at boundaries can confuse networks, leading to discontinuous loss and regression inconsistency. In this paper, we propose an efficient multi-directional object detection framework named Direction Prediction Redefinition (DPR). We describe the angle variation of rotated bounding boxes ($B_{r}$) as changes in the dimensions of horizontal bounding boxes ($B_{h}$). Specifically, we generate two sets of horizontal bounding boxes by predicting the center points of the corresponding boundaries within the rotated bounding box, thereby avoiding boundary issues caused by angle prediction. To further achieve robust rotated boundary representation, we propose the Joint Scale Representation method and the State Feature Encoding module, which are used to eliminate outliers in rotated boundaries and guide the correct selection of horizontal bounding box vertices, respectively. Moreover, we further abstract DPR as Multiple Trigonometric functions based DPR (DPR-MT). This method maps a single angle into four sets of trigonometric functions and considers them as the four sides of the horizontal bounding box. This approach predicts angles in the form of horizontal bounding boxes without complex operations, making it plug-and-play. Experimental results and visual analysis on challenging datasets further verify the effectiveness and competitiveness of our proposed method.

Transformers show a great impact on visual tracking thanks to their powerful representation learning capabilities. As the capacity of the model grows, the speed of the tracker tends to decrease gradually. Our work focuses on dealing with massively redundant information in tracking sequences with the Saliency Region Tracker (SRTrack). SRTrack is a heuristic two-stage tracker consisting of a lightweight tracking stage and a saliency stage. The former can handle simple tracking sequences while the latter is designed to perform delicate tracking on challenging frames with more discriminative features. However, the two-stage design leads to feature extrapolation, creating inconsistencies between training and inference features. In order to mitigate this problem, we develop an attention scaling factor that guarantees model robustness while yielding a slight performance gain. Our SRTrack achieves a state-of-the-art 0.699 AUC running at 61 FPS on LaSOT. Several experiments on large benchmarks demonstrate the high efficiency and accuracy of SRTrack.

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the common lesser-spoken languages relatively unexplored. Thus, in this work, we present a GNN-based framework that integrates cross-lingual word embeddings into the process of graph knowledge distillation for detecting events in low-resource language data streams. To achieve this, a novel cross-lingual knowledge distillation framework, called CLKD, exploits prior knowledge learned from similar threads in English to make up for the paucity of annotated data. Specifically, to extract sufficient useful knowledge, we propose a hybrid distillation method that consists of both feature-wise and relation-wise information. To transfer both kinds of knowledge in an effective way, we add a cross-lingual module in the feature-wise distillation to eliminate the language gap and selectively choose beneficial relations in the relation-wise distillation to avoid distraction caused by teachers’ misjudgments. Our proposed CLKD framework also adopts different configurations to suit both offline and online situations. Experiments on real-world datasets show that the framework is highly effective at detection in languages where training samples are scarce.

Recommender systems have been widely adopted in various online personal e-commerce applications for improving user experience. A long-standing challenge in recommender systems is how to provide accurate recommendation to users in cold-start situations where only a few user-item interactions can be observed. Recently, meta learning methods provide a promising solution, and most of them follow a way of parameter initialization where predictions can be fast adapted via multiple gradient descent steps. While these meta-learning recommenders promote model performance, how to derive a fundamental paradigm that enables both flexible approximations of complex user interaction distributions and effective task adaptations of global knowledge still remains a critical yet under-explored problem. To this end, we present the Flow-based Adaptive Neural Process (FANP), a new probabilistic meta-learning model where estimating the preference of each user is governed by an underlying stochastic process. Following an encoder-decoder generative framework, FANP is an effective few-shot function estimator that directly maps limited user interactions to a predictive distribution without complicated gradient updates. Through introducing a conditional normalization flow-based encoder, FANP can get rid of the model bias on latent variables and thereby derive more flexible variational distributions. Meanwhile, we propose a task-adaptive mechanism capturing the relevance of different tasks for improving adaptation ability of global knowledge. The learned task-specific and task-relevant representations are simultaneously exploited to generate the decoder parameters via a novel modulation-augmented hypernetwork. FANP is evaluated on both scenario-specific and user-specific cold-start recommendations on various real-world datasets. Extensive experimental results and detailed model analyses demonstrate that our model yields superior performance compared with multiple state-of-the-art meta-learning recommenders.

Graph pooling technique as the essential component of graph neural networks has gotten increasing attention recently and it aims to learn graph-level representations for the whole graph. Besides, graph pooling is important in graph classification and graph generation tasks. However, current graph pooling methods mainly coarsen a sequence of small-sized graphs to capture hierarchical structures, potentially resulting in the deterioration of the global structure of the original graph and influencing the quality of graph representations. Furthermore, these methods artificially select the number of graph pooling layers for different graph datasets rather than considering each graph individually. In reality, the structure and size differences among graphs necessitate a specific number of graph pooling layers for each graph. In this work, we propose reinforced pooling graph neural networks via adaptive hybrid graph coarsening networks. Specifically, we design a hybrid graph coarsening strategy to coarsen redundant structures of the original graph while retaining the global structure. In addition, we introduce multi-agent reinforcement learning to adaptively perform the graph coarsening process to extract the most representative coarsened graph for each graph, enhancing the quality of graph-level representations. Finally, we design graph-level contrast to improve the preservation of global information in graph-level representations. Extensive experiments with rich baselines on six benchmark datasets show the effectiveness of ReiPool1.

Real-world social events typically exhibit a severe class-imbalance distribution, which makes the trained detection model encounter a serious generalization challenge. Most studies solve this problem from the frequency perspective and emphasize the representation or classifier learning for tail classes. While in our observation, compared to the rarity of classes, the calibrated uncertainty estimated from well-trained evidential deep learning networks better reflects model performance. To this end, we propose a novel uncertainty-guided class imbalance learning framework - UCL$_{SED}$, and its variant - UCL-EC$_{SED}$, for imbalanced social event detection tasks. We aim to improve the overall model performance by enhancing model generalization to those uncertain classes. Considering performance degradation usually comes from misclassifying samples as their confusing neighboring classes, we focus on boundary learning in latent space and classifier learning with high-quality uncertainty estimation. First, we design a novel uncertainty-guided contrastive learning loss, namely UCL and its variant - UCL-EC, to manipulate distinguishable representation distribution for imbalanced data. During training, they force all classes, especially uncertain ones, to adaptively adjust a clear separable boundary in the feature space. Second, to obtain more robust and accurate class uncertainty, we combine the results of multi-view evidential classifiers via the Dempster-Shafer theory under the supervision of an additional calibration method. We conduct experiments on three severely imbalanced social event datasets including Events2012_100, Events2018_100, and CrisisLexT_7. Our model significantly improves social event representation and classification tasks in almost all classes, especially those uncertain ones.

Detecting significant communities via an algorithmic game-theoretic model has recently shown great promise, which seeks to formulate community detection as a competitive game, enabling us to study the network's potential structure with a systematic tool. However, fully leveraging its potential to uncover the mechanism behind community formation remains a challenge. Here we proposeSCG—a Sequential Community Game model to track and characterize the network's structural property. Unlike conventional formulations where individual nodes are treated as players, our model considers communities as players who strive to maximize their structural utility by strategically selecting member nodes. By prioritizing significant communities sequentially,SCGenables differentiation between uncovered communities. Importantly, we establish the existence of a strict Nash equilibrium inSCG, suggesting its ability to capture a stable community structure. We run extensive experiments on several synthetic and real-world networks to testSCG's performance. Results show thatSCGcan help us well track the network's structural properties and also give us reliable performance compared to related baselines.

Graph Neural Networks (GNNs) have achieved impressive performance in many tasks on graph data. Recent studies show that they are vulnerable to adversarial attacks. Deliberate and unnoticeable perturbations on topology structure could render them near-useless in applications. How to design effective methods to improve the robustness of GNNs is a crucial problem. To solve this problem, some works attempt to design more robust GNN models, while others attempt to remove perturbations from the poisoned graph. Different from the previous works, this paper proposes a general framework termed asGraphReshapeto enhance the robustness of GNNs via directly correcting the shifted classification boundary of GNN models in the presence of adversarial attacks.GraphReshapeconsists of two modules:locating tractive nodesthat could correct GNNs andreshaping local structureto improve their representations in the latent space. Extensive experiments on four real-world datasets show thatGraphReshapeachieves significant performance gain compared with state-of-the-art baselines against different adversarial attacks.

CTR (Click-Through Rate) prediction plays an essential role in online advertising systems. Most existing works attempt to capture users’ interests from sessions by assuming that behaviors within a session are homogeneous. However, user interest may change frequently. Thus it is hard to guarantee that behaviors in a session are homogeneous, resulting in users’ interests extracted from sessions being biased. In this paper, we propose a model named Deep Session Heterogeneity-aware Network (DSHN) by learning the relationships of behaviors within sessions and the relevance between the session and target item to alleviate the influence of irrelevant or heterogeneous sessions. We design a heterogeneity-aware mechanism to learn the heterogeneity of items within a session. Then we further design two modules: the Session Heterogeneity Learning module and the Relevance Inference module. The Session Heterogeneity Learning module weighs each session by summarizing the variation of session interest with and without any behavior. The relevance Inference module learns the relevance between the target item and each session in a similar way by learning session interest with and without the target item. Extensive experiments on four datasets demonstrate that our proposed DSHN achieves better results compared to the state-of-the-art.

Event extraction (EE) is a crucial research task for promptly apprehending event information from massive textual data. With the rapid development of deep learning, EE based on deep learning technology has become a research hotspot. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey. This article fills the research gap by reviewing the state-of-the-art approaches, especially focusing on the general domain EE based on deep learning models. We introduce a new literature classification of current general domain EE research according to the task definition. Afterward, we summarize the paradigm and models of EE approaches, and then discuss each of them in detail. As an important aspect, we summarize the benchmarks that support tests of predictions and evaluation metrics. A comprehensive comparison among different approaches is also provided in this survey. Finally, we conclude by summarizing future research directions facing the research area.

Detecting a community in a network is a matter of discerning the distinct features and connections of a group of members that are different from those in other communities. The ability to do this is of great significance in network analysis. However, beyond the classic spectral clustering and statistical inference methods, there have been significant developments with deep learning techniques for community detection in recent years-particularly when it comes to handling high-dimensional network data. Hence, a comprehensive review of the latest progress in community detection through deep learning is timely. To frame the survey, we have devised a new taxonomy covering different state-of-the-art methods, including deep learning models based on deep neural networks (DNNs), deep nonnegative matrix factorization, and deep sparse filtering. The main category, i.e., DNNs, is further divided into convolutional networks, graph attention networks, generative adversarial networks, and autoencoders. The popular benchmark datasets, evaluation metrics, and open-source implementations to address experimentation settings are also summarized. This is followed by a discussion on the practical applications of community detection in various domains. The survey concludes with suggestions of challenging topics that would make for fruitful future research directions in this fast-growing deep learning field.

Transfer learning-based recommendation mitigates the sparsity of user-item interactions by introducing auxiliary domains. Social influence extracted from direct connections between users typically serves as an auxiliary domain to improve prediction performance. However, direct social connections also face severe data sparsity problems that limit model performance. In contrast, users’ dependency on communities is another valuable social information that has not yet received sufficient attention. Although studies have incorporated community information into recommendation by aggregating users’ preferences within the same community, they seldom capture the structural discrepancies among communities and the influence of structural discrepancies on users’ preferences. To address these challenges, we propose a community-preserving recommendation framework with cyclic transfer learning, incorporating heterogeneous community influence into the rating domain. We analyze the characteristics of the community domain and its inter-influence on the rating domain, and construct link constraints and preference constraints in the community domain. The shared vectors that bridge the rating domain and the community domain are allowed to be more consistent with the characteristics of both domains. Extensive experiments are conducted on four real-world datasets. The results manifest the excellent performance of our approach in capturing real users’ preferences compared with other state-of-the-art methods.

Special Issue Part 1 (Issue 3) and Part 2 (Issue 4) of AIEDAM are based on a workshop on Learning and Creativity held at the 2002 conference on Artificial Intelligence in Design, AID '02 (www.cad.strath.ac.uk/AID02_workshop/Workshop_webpage.html; Gero, ...

Social Event Detection has become increasingly important as a way of letting the public know about significant global events in a clear and timely fashion. However, current methods are still unsatisfactory for detecting events due to the complexity of reality social networks. Specifically, there exist overlinks for partial nodes (i.e., messages), and conversely, some nodes lack sufficient neighborhood information. In addition, the time interval between different messages in social networks should also be fully considered by existing shallow GNN models. What is needed is an approach that can improve the embedding ability of GNN models by extracting and aggregating more se-mantic and structural information from the same graph for more representative and robust message embeddings, rather than constructing a richer message graph by adding additional attributed data. To this end, we design an innovative Reinforced Deep Heterogeneous Graph Attention Network (Re-DHAN) method for offline and incremental social event detection tasks. The framework initially leverages multi-agent reinforcement learning to select the most meaningful neighbors from various meta-path graphs to avoid redundant links. Then, our approach adds temporal convolutional attention across the semantics and timestamps for all nodes, ensuring a comprehensive capture of both semantic and time elements within social networks. Finally, to ensure that the embeddings produced by DHAN are both robust to too few neighbors and highly representative, we constructed a new Dual Graph Contrastive Learning model, called DGCL, to simulate the missing structural information. DGCL includes a triplet loss function and an unsupervised GraphCL model with multi-scaled subgraph augmentation. A series of experiments in offline and incremental social event detection demonstrates Re-DHAN as superior to the current state-of-the-art baselines. Furthermore, the results show that our ReDHAN has powerful and robust abilities to capture, extract, and aggregate the semantic and structural information within graphs.

How to satisfy safety constraints almost surely (or with probability one) is becoming an emerging research issue for safe reinforcement learning (RL) algorithms in safety-critical domains. For instance, self-driving cars are expected to ensure that the driving strategy they adopt will never do harm to pedestrians and themselves. However, existing safe RL algorithms suffer from either risky and unstable constraint satisfaction or slow convergence. To tackle these two issues, we propose Conservatively Constrained Policy Optimization (CCPO) using state augmentation. CCPO designs a simple yet effective penalized reward function by introducing safety states and adaptive penalty factors under Safety Augmented MDP framework. Specifically, a novel Safety Promotion Function (SPF) is proposed to make the agent being more concentrated on constraint satisfaction with faster convergence by reshaping a more conservative constrained optimization objective. Moreover, we theoretically prove the convergence of CCPO. To validate both the effectiveness and efficiency of CCPO, comprehensive experiments are conducted in both single-constraint and more challenging multi-constraint environments. The experimental results demonstrate that the safe RL algorithms augmented by CCPO satisfy the predefined safety constraints almost surely and gain almost equivalent cumulative reward with faster convergence.

Most existing cross-domain facial expression recognition (FER) works require target domain data to assist the model in analyzing distribution shifts to overcome negative effects. However, it is often hard to obtain expression images of the target domain in practical applications. Moreover, existing methods suffer from the interference of identity information, thus limiting the discriminative ability of the expression features. We exploit the idea of domain generalization (DG) and propose a representation disentanglement model to address the above problems. Specifically, we learn three independent potential subspaces corresponding to the domain, expression, and identity information from facial images. Meanwhile, the extracted expression and identity features are recovered as Fourier phase information reconstructed images, thereby ensuring that the high-level semantics of images remain unchanged after disentangling the domain information. Our proposed method can disentangle expression features from expression-irrelevant ones (i.e., identity and domain features). Therefore, the learned expression features exhibit sufficient domain invariance and discriminative ability. We conduct experiments with different settings on multiple benchmark datasets, and the results show that our method achieves superior performance compared with state-of-the-art methods.

Graph Transformers (GTs) have proved their advantage in graph-level tasks. However, existing GTs still perform unsatisfactorily on the node classification task due to 1) the overwhelming unrelated information obtained from a vast number of irrelevant distant nodes and 2) the quadratic complexity regarding the number of nodes via the fully connected attention mechanism. In this paper, we present Gapformer, a method for node classification that deeply incorporates Graph Transformer with Graph Pooling. More specifically, Gapformer coarsens the large-scale nodes of a graph into a smaller number of pooling nodes via local or global graph pooling methods, and then computes the attention solely with the pooling nodes rather than all other nodes. In such a manner, the negative influence of the overwhelming unrelated nodes is mitigated while maintaining the long-range information, and the quadratic complexity is reduced to linear complexity with respect to the fixed number of pooling nodes. Extensive experiments on 13 node classification datasets, including homophilic and heterophilic graph datasets, demonstrate the competitive performance of Gapformer over existing Graph Neural Networks and GTs.

Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation. As an essential component of the architecture, graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph. Although a great variety of methods have been proposed in this promising and fast-developing research field, to the best of our knowledge, little effort has been made to systematically summarize these works. To set the stage for the development of future works, in this paper, we attempt to fill this gap by providing a broad review of recent methods for graph pooling. Specifically, 1) we first propose a taxonomy of existing graph pooling methods with a mathematical summary for each category; 2) then, we provide an overview of the libraries related to graph pooling, including the commonly used datasets, model architectures for downstream tasks, and open-source implementations; 3) next, we further outline the applications that incorporate the idea of graph pooling in a variety of domains; 4) finally, we discuss certain critical challenges facing current studies and share our insights on future potential directions for research on the improvement of graph pooling.

The anonymity of online networks makes tackling fraud increasingly costly. Thanks to the superiority of graph representation learning, graph-based fraud detection has made significant progress in recent years. However, upgrading fraudulent strategies produces more advanced and difficult scams. One common strategy is synergistic camouflage —— combining multiple means to deceive others. Existing methods mostly investigate the differences between relations on individual frauds, that neglect the correlation among multi-relation fraudulent behaviors. In this paper, we design several statistics to validate the existence of synergistic camouflage of fraudsters by exploring the correlation among multi-relation interactions. From the perspective of multi-relation, we find two distinctive features of fraudulent behaviors, i.e., alienation and marginalization. Based on the finding, we propose COFRAUD, a correlation-aware fraud detection model, which innovatively incorporates synergistic camouflage into fraud detection. It captures the correlation among multi-relation fraudulent behaviors. Experimental results on two public datasets demonstrate that COFRAUD achieves significant improvements over state-of-the-art methods.

Long sequence time-series forecasting has important applications in long-term planning management scenarios. Researches based on Transformer effectively improve the capability for long sequence forecasting, but the quadratic computing complexity causes high resource consumption, limiting its application in long sequence scenarios. Meanwhile, many studies use the dot-product attention mechanism to model time dependency, but don't model the sequential information of time-series. It prevents the capture of more efficient long-term time dependencies. In addition, in the latest researches combining decomposition methods, there are the problem of trend information loss and the limitation of not being able to peel off more subdivided time patterns, which restrict the improvement of prediction ability. Therefore, we propose a Transformer-based model, Segformer. Firstly, Segformer extracts multiple components with obvious dependencies and coordinates the modeling process with the help of multi-component decomposition blocks and collaboration blocks. Secondly, SegAttention, a new variant of the attention mechanism with$O((\frac{L}{l})^{2})$computation complexity (whole sequence length L, segment length$l$), is proposed to model the dependencies between segments according to the values and orders in the segment sequences, and aggregate segment-level information. Experiments on five real datasets show that Segformer respectively reduces the forecasting error by about 13% and 22% compared with the two advanced benchmarks, and Segformer offers an efficient solution for long-term dependency modeling problem of time-series.

In the era of the Industrial Internet of Things, anomaly detection is important for real-world applications. However, most streaming data lack meaningful labels. Furthermore, some anomalies of streaming data may be concept drift, but few methods can deal with it. To address these challenges, we propose an unsupervised anomaly detection solution that can deal with streaming data, called OOA-UADS (Offline, Online, Analysis-an Unsupervised Anomaly Detection Solution for Multivariate Time Series). The solution consists of three stages: offline training, online prediction and anomaly analysis. Time convolutional networks and variational autoencoders are used to deconstruct and reconstruct the multivariate time series data to learn the normal patterns. The anomaly inversion mechanism identifies concept drift in the anomaly prediction stage by dynamically updating the classification thresholds. Intelligent anomaly analysis then provides anomaly dimensions to help engineers better analyse the anomalous behaviour. Our experiments show that OOA-UADS performs satisfactorily. On seven streaming datasets, OOA-UADS outperforms 11 baselines in terms of AUC and provides state-of-the-art F1 scores on three batch datasets.

Current research on online public opinion regarding the coronavirus disease in 2019 (COVID-19) leverages keyword extraction, sentiment analysis, and topic modeling to analyze online public opinion. The multi-granularity features of online public opinions and semantic relations between the features, how-ever, remain less explored. Reliance on only topics or keywords for measuring public opinion is insufficient as topics are too broad and keywords too narrow. Analysis at an intermediate level, which most studies overlook, is crucial in gaining a clearer insight into public opinion. Additionally, exploring the semantic relationships between components of online public opinion can shed light on the logical connections between them and help understand how they interact in the dissemination of online public opinion, leading to a better understanding of its evolution mechanism. We conducted a public opinion analysis on Worldwide COVID-19 outbreaks via Topic Knowledge Graph. Specifically, we first use the Combined Topic Model to extract public opinion topics. Then multi-dimensions attributes of the topic such as [subject, predicate, object] triples, topic popularity, and topic emotion intensity are extracted. Subsequently, the semantic relations of different public opinion topics are calculated from the two levels of predicates co-occurrence and subject-object sharing. Finally, we applied the constructed framework to the public opinion information related to COVID-19 and analyzed the characteristics in the evolution of online public opinion.

Graph-level anomaly detection aims at capturing anomalous individual graphs in a graph set. Due to its significance in various real-world application fields, e.g., identifying rare molecules in chemistry and detecting potential frauds in online social networks, graph-level anomaly detection has received great attention recently. In distinction from node- and edge-level anomaly detection that is devoted to identifying anomalies on a single graph, graph-level anomaly detection faces more significant challenges because both the intra- and inter- graph structural and attribute patterns need to be taken into account to distinguish anomalies that exhibit deviating structures, rare attributes or the both. Although deep graph representation learning shows effectiveness in fusing high-level representations and capturing characters of individual graphs, most of the existing works are defective in graph-level anomaly detection because of their limited capability in exploring information across graphs, the imbalanced data distribution of anomalies, and low interpretability of the black-box graph neural networks (GNNs). To overcome these limitations, we propose a novel deep evolutionary graph mapping framework named GmapAD1, which can adaptively map each graph into a new feature space based on its similarity to a set of representative nodes chosen from the graph set. By automatically adjusting the candidate nodes using a specially designed evolutionary algorithm, anomalies and normal graphs are mapped to separate areas in the new feature space where a clear boundary between them can be learned. The selected candidate nodes can therefore be regarded as a benchmark for explaining anomalies because anomalies are more dissimilar/similar to the benchmark than normal graphs. Through our extensive experiments on nine real-world datasets, we demonstrate that exploring both intra- and inter- graph structural and attribute information is critical to spot anomalous graphs, and our method has achieved statistically significant improvements compared to the state of the art in terms of precision, recall, F1 score, and AUC.

The proliferation of fake news in social media has been recognized as a severe problem for society, and substantial attempts have been devoted to fake news detection to alleviate the detrimental impacts. Knowledge graphs (KGs) comprise rich factual relations among real entities, which could be utilized as ground-truth databases and enhance fake news detection. However, most of the existing methods only leveraged natural language processing and graph mining techniques to extract features of fake news for detection and rarely explored the ground knowledge in knowledge graphs. In this work, we propose a novel Heterogeneous Graph Neural Network via Knowledge Relations for Fake News Detection (HGNNR4FD). The devised framework has four major components: 1) A heterogeneous graph (HG) built upon news content, including three types of nodes, i.e., news, entities, and topics, and their relations. 2) A KG that provides the factual basis for detecting fake news by generating embeddings via relations in the KG. 3) A novel attention-based heterogeneous graph neural network that can aggregate information from HG and KG, and 4) a fake news detector, which is capable of identifying fake news based on the news embeddings generated by HGNNR4FD. We further validate the performance of our method by comparison with seven state-of-art baselines and verify the effectiveness of the components through a thorough ablation analysis. From the results, we empirically demonstrate that our framework achieves superior results and yields improvement over the baselines regarding evaluation metrics of accuracy, precision, recall, and F1-score on four real-world datasets.

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been studied, which brings the limitation in applying it to real-world applications. Contrastive learning identifies the samples with the negative ones from the noise distribution that changes in the incremental scenarios. Therefore, only fitting the change of data without noise distribution causes bias, and directly retraining results in low efficiency. To bridge this research gap, we propose a self-supervised Incremental Contrastive Learning (ICL) framework consisting of (i) a novel Incremental InfoNCE (NCE-II) loss function by estimating the change of noise distribution for old data to guarantee no bias with respect to the retraining, (ii) a meta-optimization with deep reinforced Learning Rate Learning (LRL) mechanism which can adaptively learn the learning rate according to the status of the training processes and achieve fast convergence which is critical for incremental learning. Theoretically, the proposed ICL is equivalent to retraining, which is based on solid mathematical derivation. In practice, extensive experiments in different domains demonstrate that, without retraining a new model, ICL achieves up to 16.7x training speedup and 16.8x faster convergence with competitive results.

Users' involvement in creating and propagating news is a vital aspect of fake news detection in online social networks. Intuitively, credible users are more likely to share trustworthy news, while untrusted users have a higher probability of spreading untrustworthy news. In this paper, we construct a dual-layer graph (i.e., news layer and user layer) to extract multi-relations of news and users in social networks to derive rich information for detecting fake news. Based on the dual-layer graph, we propose a fake news detection model Us-DeFake. It learns the propagation features of news in the news layer and the interaction features of users in the user layer. Through the inter-layer in the graph, Us-DeFake fuses the user signals that contain credibility information into the news features, to provide distinctive user-aware embeddings of news for fake news detection. The training process conducts on multiple dual-layer subgraphs obtained by a graph sampler to scale Us-DeFake in large scale social networks. Extensive experiments on real-world datasets illustrate the superiority of Us-DeFake which outperforms all baselines, and the users' credibility signals learned by interaction relation can notably improve the performance of our model.

Graph neural networks (GNNs) are now the mainstream method for mining graph-structured data and learning low-dimensional node- and graph-level embeddings to serve downstream tasks. However, limited by the bottleneck of interpretability that deep neural networks present, existing GNNs have ignored the issue of estimating the appropriate number of dimensions for the embeddings. Hence, we propose a novel framework called Minimum Graph Entropy principle-guided Dimension Estimation, i.e. MGEDE, that learns the appropriate embedding dimensions for both node and graph representations. In terms of node-level estimation, a minimum entropy function that counts both structure and attribute entropy, appraises the appropriate number of dimensions. In terms of graph-level estimation, each graph is assigned a customized embedding dimension from a candidate set based on the number of dimensions estimated for the node-level embeddings. Comprehensive experiments with node and graph classification tasks and nine benchmark datasets verify the effectiveness and generalizability of MGEDE.

Learning unbiased node representations for imbalanced samples in the graph has become a more remarkable and important topic. For the graph, a significant challenge is that the topological properties of the nodes (e.g., locations, roles) are unbalanced (topology-imbalance), other than the number of training labeled nodes (quantity-imbalance). Existing studies on topology-imbalance focus on the location or the local neighborhood structure of nodes, ignoring the global underlying hierarchical properties of the graph, i.e., hierarchy. In the real-world scenario, the hierarchical structure of graph data reveals important topological properties of graphs and is relevant to a wide range of applications. We find that training labeled nodes with different hierarchical properties have a significant impact on the node classification tasks and confirm it in our experiments. It is well known that hyperbolic geometry has a unique advantage in representing the hierarchical structure of graphs. Therefore, we attempt to explore the hierarchy-imbalance issue for node classification of graph neural networks with a novelty perspective of hyperbolic geometry, including its characteristics and causes. Then, we propose a novel hyperbolic geometric hierarchy-imbalance learning framework, named HyperIMBA, to alleviate the hierarchy-imbalance issue caused by uneven hierarchy-levels and cross-hierarchy connectivity patterns of labeled nodes. Extensive experimental results demonstrate the superior effectiveness of HyperIMBA for hierarchy-imbalance node classification tasks.

Graph neural networks (GNNs) are powerful models to handle graph data and can achieve state-of-the-art in many critical tasks including node classification and link prediction. However, existing graph neural networks still face both challenges of over-smoothing and over-squashing based on previous literature. To this end, we propose a new Curvature-based topology-aware Dropout sampling technique named CurvDrop, in which we integrate the Discrete Ricci Curvature into graph neural networks to enable more expressive graph models. Also, this work can improve graph neural networks by quantifying connections in graphs and using structural information such as community structures in graphs. As a result, our method can tackle the both challenges of over-smoothing and over-squashing with theoretical justification. Also, numerous experiments on public datasets show the effectiveness and robustness of our proposed method. The code and data are released in https://github.com/liu-yang-maker/Curvature-based-Dropout.

Social Internet of Things (SIoT), a promising and emerging paradigm that injects the notion of social networking into smart objects (i.e., things), paving the way for the next generation of Internet of Things. However, due to the risks and uncertainty, a crucial and urgent problem to be settled is establishing reliable relationships within SIoT, that is, trust evaluation. Graph neural networks for trust evaluation typically adopt a straightforward way such as one-hot or node2vec to comprehend node characteristics, which ignores the valuable semantic knowledge attached to nodes. Moreover, the underlying structure of SIoT is usually complex, including both the heterogeneous graph structure and pairwise trust relationships, which renders hard to preserve the properties of SIoT trust during information propagation. To address these aforementioned problems, we propose a novel knowledge-enhanced graph neural network (KGTrust) for better trust evaluation in SIoT. Specifically, we first extract useful knowledge from users’ comment behaviors and external structured triples related to object descriptions, in order to gain a deeper insight into the semantics of users and objects. Furthermore, we introduce a discriminative convolutional layer that utilizes heterogeneous graph structure, node semantics, and augmented trust relationships to learn node embeddings from the perspective of a user as a trustor or a trustee, effectively capturing multi-aspect properties of SIoT trust during information propagation. Finally, a trust prediction layer is developed to estimate the trust relationships between pairwise nodes. Extensive experiments on three public datasets illustrate the superior performance of KGTrust over state-of-the-art methods.

Graph Neural Networks (GNNs) are de facto solutions to structural data learning. However, it is susceptible to low-quality and unreliable structure, which has been a norm rather than an exception in real-world graphs. Existing graph structure learning (GSL) frameworks still lack robustness and interpretability. This paper proposes a general GSL framework, SE-GSL, through structural entropy and the graph hierarchy abstracted in the encoding tree. Particularly, we exploit the one-dimensional structural entropy to maximize embedded information content when auxiliary neighbourhood attributes is fused to enhance the original graph. A new scheme of constructing optimal encoding trees are proposed to minimize the uncertainty and noises in the graph whilst assuring proper community partition in hierarchical abstraction. We present a novel sample-based mechanism for restoring the graph structure via node structural entropy distribution. It increases the connectivity among nodes with larger uncertainty in lower-level communities. SE-GSL is compatible with various GNN models and enhances the robustness towards noisy and heterophily structures. Extensive experiments show significant improvements in the effectiveness and robustness of structure learning and node representation learning.

Social networks are a crucial component of the Internet of People (IoP), which represents cutting-edge of Internet of Things (IoT). Predicting a large number of unknown node labels with few known labels is one of the challenging problems in social network analysis. Fortunately, the graph convolutional network (GCN) and subsequent variants have achieved remarkable performance on semi-supervised node classification (SSNC). However, previous works only focus on the case of clean labels and rarely study the problem of SSNC under noisy labels (SSNCNL), which is a more challenging and practical problem in the realm of weakly supervised learning. To cope with the aforementioned challenge, we present a novel dual mutual robust GCN named DMRGCN with inspiration from deep mutual learning and robust learning in the domain of image recognition. Specifically, we first employ two GCNs with different learning abilities to construct network architecture. Then, we define a joint loss function which consists of a weighted combination of supervised loss, mutual loss, and robust loss. Finally, we train the network under the pseudo-siamese network paradigm. Experimental results on three social network benchmark datasets with different levels of noise on labels demonstrate that DMRGCN outperforms the vanilla GCN and several variants on classification accuracy. In particular, under the two conditions of labels without noise and with noise, the node classification accuracy obtained by our proposed DMRGCN can be 3.05% and 6.44% higher than that of the vanilla GCN, respectively.

Existing works on session-based recommendation have shown the advantage in enhancing the prediction ability of recommendation with various deep learning techniques. However, the following challenges need to be addressed: (1) the hierarchy of item transition patterns is overlooked; (2) existing works fail to distinguish various factors of item transition within a single session for disentangling user intents. To cope with the above challenges, we propose a novel session based recommendation model called S elf-supervised D ual H ypergraph learning with I ntent D isentanglement model ( SDHID ). Specifically, we first propose a disentangled capsule hypergraph convolutional channel for ne-grained intent learning to capture the intra-session pattern. Accordingly, we introduce the hypergraph and capsule networks in disentangling to learn the item embedding for different factors, and then the representation of the intra-session pattern is obtained by aggregating item embedding with attention weights. Moreover, we build a novel dual–primal hypergraph convolutional channel by mapping the hypergraph to a dual–primal graph for learning the item transition pattern of inter-session. In addition, the above two channels are combined into a self-supervised contrastive learning framework by maximizing mutual information between the learned session representations. We unify the recommendation and the self-supervised tasks under a primary and auxiliary learning framework. The combined optimization of two tasks leads to a hierarchical joint learning item transition for intra- and inter-session. Extensive experiments on real datasets show that the proposed model outperforms several state-of-the-art models.

While graph representation learning methods have shown success in various graph mining tasks, what knowledge is exploited for predictions is less discussed. This paper proposes a novel Adaptive Subgraph Neural Network named AdaSNN to find critical structures in graph data, i.e., subgraphs that are dominant to the prediction results. To detect critical subgraphs of arbitrary size and shape in the absence of explicit subgraph-level annotations, AdaSNN designs a Reinforced Subgraph Detection Module to search subgraphs adaptively without heuristic assumptions or predefined rules. To encourage the subgraph to be predictive at the global scale, we design a Bi-Level Mutual Information Enhancement Mechanism including both global-aware and label-aware mutual information maximization to further enhance the subgraph representations in the perspective of information theory. By mining critical subgraphs that reflect the intrinsic property of a graph, AdaSNN can provide sufficient interpretability to the learned results. Comprehensive experimental results on seven typical graph datasets demonstrate that AdaSNN has a significant and consistent performance improvement and provides insightful results.

Tracking the evolution of clusters in social media streams is becoming increasingly important for many applications, such as early detection and monitoring of natural disasters or pandemics. In contrast to clustering on a static set of data, streaming data clustering does not have a global view of the complete data. The local (or partial) view in a high-speed stream makes clustering a challenging task. In this paper, we propose a novel density peak based algorithm,TStream, for tracking the evolution of clusters and outliers in social media streams, via the evolutionary actions of cluster adjustment, emergence, disappearance, split, and merge.TStreamis based on a temporal decay model and text stream summarisation. The decay model captures the decreasing importance of textual documents over time. The stream summarisation compactly represents them with the help of cells (akamicro-clusters) in the memory. We also propose a novel efficient index calledshared dependency tree(akaSD-Tree) based on the ideas of density peak and shared dependency. It maintains the dynamic dependency relationships inTStreamand thereby improves the overall efficiency. We conduct extensive experiments on five real datasets.TStreamoutperforms the existing state-of-the-art solutions based onMStream,MStreamF,EDMStream,OSGM, andEStream, in terms of cluster mapping measure (CMM) by up to 17.8%, 18.6%, 6.9%, 16.4%, and 20.1%, respectively. It is also significantly more efficient thanMStream,MStreamF,OSGM, andEStream, in terms of response time and throughput.

Aspect-level sentiment classification (ASC) seeks to reveal the emotional tendency of a designated aspect of a text. Some researchers have recently tried to exploit large amounts of document-level sentiment classification (DSC) data available to help improve the performance of ASC models through transfer learning. However, these studies often ignore the difference in sentiment distribution between document-level and aspect-level data without preprocessing the document-level knowledge. Our study provides a transfer learning with document-level data augmentation (TL-DDA) framework to transfer more accurate document-level knowledge to the ASC model by means ofdocument-level data augmentationandattention fusion. First, we usedocument data selectionandtext concatenationto produce document-level data with various sentiment distributions. The augmented document data is then utilized for pre-training a well-designed DSC model. Finally, afterattention adjustment, wefuse the word attentionobtained from this DSC model into the ASC model. Results of experiments utilizing two publicly available datasets suggest that TL-DDA is reliable.

Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As different event types always own distinct extraction schemas (i.e., role patterns), previous work on EE usually follows an isolated learning paradigm, performing element extraction independently for different event types. It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles. This paper proposes a novel neural association framework for the EE task. Given a document, it first performs type classification via constructing a document-level event graph to associate sentence nodes of different types and adopting a document-awared graph attention network to learn sentence embeddings. Then, element extraction is achieved by building a new schema of argument roles, with a type-awared parameter inheritance mechanism to enhance role preference for extracted elements. As such, our model takes into account type and role associations during EE, enabling implicit information sharing among them. Experimental results show that our approach consistently outperforms most state-of-the-art EE methods in both sub-tasks, especially at least 2.51% and 1.12% improvement of the event trigger identification and argument role classification sub-tasks. Particularly, for types/roles with less training data, the performance is superior to the existing methods.

Graphs have been widely adopted to accomplish fraud detection tasks because of their inherently favorable structure to capture the intricate features in many complicated scenarios, especially in some modern e-commerce situations that have various relation attributes like transactions. These works tend to utilize the direct aggregate information about neighbor nodes of the target node or the aggregation of the neighbor information after the conditional filter and mostly use local information but ignore global information. However, in some cases, local abnormal points are detected in the global view, so global information is very important for fraud detection. In this article, we propose a local and global aware memory-based graph neural network for fraud detection (LGM-GNN). It first obtains the preliminary node embedding through relation-aware embedding and then interactively aggregates the local and global memory network to fuse and utilize the local and global information. Finally, the node embeddings of different levels are aggregated through the hierarchical information aggregator. Extensive experiments show our proposed LGM-GNN outperforms other SOAT methods on two real-world fraud detection datasets.

The goal of crime prediction is to forecast the number of crime incidents at each region of a city based on the historical crime data. It has attracted a great deal of attention from both academic and industrial communities due to its considerable significance in improving urban safety and reducing financial losses. Although much progress has been made in this field, most of the existing approaches assume that the historical crime data are complete, which does not hold in many real-world scenarios. Meanwhile, crime incidents are affected by multiple factors and have intricate spatial, temporal, and categorical correlations, which are not fully utilized by the current methods. In this article, we propose a novel tensor decomposition based framework, named TD-Crime, to conduct prediction directly on the incomplete crime data. Specifically, we first organize the crime data as a tensor and then apply the nonnegative CP decomposition to it, which not only provides a natural solution to the missing data problem but also captures the spatial, temporal, and categorical correlations implicitly. Moreover, we attempt to exploit the spatial and temporal correlations explicitly by directly learning from the crime data to further improve the forecasting performance. Finally, we obtain a joint optimization problem and present an efficient alternating optimization scheme to find a satisfactory solution. Extensive experiments on the real-world crime datasets show that TD-Crime can address the crime prediction task effectively under different missing data scenarios.

Oriented object detection has made astonishing progress. However, existing methods neglect to address the issue of false positives caused by the background or nearby clutter objects. Meanwhile, class imbalance and boundary overflow issues caused by the predicting rotation angles may affect the accuracy of rotated bounding box predictions. To address the above issues, we propose a Single-stage Rotate object detector via Dense prediction and False positive suppression (SRDF). Specifically, we design an Instance-level False Positive Suppression Module (IFPSM), IFPSM acquires the weight information of target and non-target regions by supervised learning of spatial feature encoding, and applies these weight values to the deep feature map, thereby attenuating the response signals of non-target regions within the deep feature map. Compared to commonly used attention mechanisms, this approach more accurately suppresses false positive regions. Then, we introduce a hybrid classification and regression method to represent the object orientation, the proposed mothed divide the angle into two segments for prediction, reducing the number of categories and narrowing the range of regression. This alleviates the issue of class imbalance caused by treating one degree as a single category in classification prediction, as well as the problem of boundary overflow caused by directly regressing the angle. In addition, we transform the traditional post-processing steps based on matching and searching to a two-dimensional probability distribution mathematical model, which accurately and quickly extracts the bounding boxes from dense prediction results. Extensive experiments on Remote Sensing, Synthetic Aperture Radar, and Scene Text benchmarks demonstrate the superiority of the proposed SRDF method over state-of-the-art rotated object detection methods. Our codes are available at https://github.com/TomZandJerryZ/SRDF.

With the development of deep learning technology, the performance of facial expression recognition (FER) has been significantly improved. The current main challenge comes from the confusion of facial expressions caused by the highly nonlinear changes of facial expressions. However, the existing FER methods based on Convolutional Neural Networks (CNN) often ignore the underlying relationship between expressions which is crucial to meliorate the performance of recognition for confusable expressions. And the methods based on Graph Convolutional Networks (GCN) can capture the relationship between vertices, but the aggregation degree of subgraphs generated by these methods is low. They are easy to include unconfident neighbors, which increases the learning difficulty of the network. To solve the above problems, this paper proposes a method to recognize facial expressions on the high aggregation subgraphs (HASs) by combing the advantages of CNN extracting features and GCN modeling complex graph patterns. Specifically, we formulate FER as a vertex prediction problem. Considering the importance of high-order neighbors and higher efficiency, we utilize vertex confidence to find high-order neighbors. Then we construct the HASs based on the top embedding features of these high-order neighbors. And we utilize the GCN to perform reasoning and infer the class of vertices for HASs without a large number of overlapping subgraphs. Our method captures the underlying relationship between expressions on the HASs and improves the accuracy and efficiency of FER. Experimental results on both the in-the-lab datasets and the in-the-wild datasets show that our method achieves higher recognition accuracy than several state-of-the-art methods. This highlights the benefit of the underlying relationship between expressions for FER.

Tourism is an important industry and a popular leisure activity involving billions of tourists per annum. One challenging problem tourists face is identifying attractive Places-of-Interest (POIs) and planning the personalized trip with time constraints. Most of the existing trip recommendation methods mainly consider POI popularity and user preferences, and focus on the last visited POI when choosing the next POI. However, the visit patterns and their asymmetry property have not been fully exploited. To this end, in this article, we present a GRM-RTrip (short for G raph-based R epresentation M ethod for R einforce Trip Recommendation) framework. GRM-RTrip learns POI representations from incoming and outgoing views to obtain asymmetric POI-POI transition probability via POI-POI graph networks, and then fuses the trained POI representation into a user-POI graph network to estimate user preferences. Finally, after formulating the personalized trip recommendation as a Markov Decision Process (MDP), we utilize a reinforcement learning algorithm for generating a personalized trip with maximal user travel experience. Extensive experiments are performed on the public datasets and the results demonstrate the superiority of GRM-RTrip compared with the state-of-the-art trip recommendation methods.

Electroencephalogram (EEG)-based applications in Brain-Computer Interfaces (BCIs, or Human-Machine Interfaces, HMIs), diagnosis of neurological disease, rehabilitation,etc, rely on supervised techniques such as EEG classification that requires given class labels or markers. Incomplete or incorrectly labeled or unlabeled EEG data are increasing with the ever-expanding amount of EEG data generated by such applications and the ambiguities these generate degrade the performance of supervised techniques. To address the challenging task of clustering EEG data with limitedprioriknowledge, we introduce a semi-supervised graph embedding EEG clustering approach termedConsEEGcwith multiple constraints,i.e., label-transformed connectivity constraints that constrains the connection or disconnection among EEG data, compactness-and-scatter constraint that constrains the intra-cluster compactness and inter-cluster scatter of EEG clusters, and fairness constraint that constrains the fair ratio of elements between EEG clusters, to make best use of limitedprioriknowledge of EEG data and to achieve better EEG clustering results.ConsEEGcis conducted with an optimization objective function that integrates pseudo label learning, least-square error minimization and multiple constraints, and it can quickly converge to local optima. The experiments demonstrate thatConsEEGccan efficiently yield good clustering results on various types of real-world EEG datasets, compared to state-of-the-art standard unsupervised and semi-supervised EEG/time series clustering algorithms.

Community detection, a fundamental task for network analysis, aims to partition a network into multiple sub-structures to help reveal their latent functions. Community detection has been extensively studied in and broadly applied to many real-world network problems. Classical approaches to community detection typically utilize probabilistic graphical models and adopt a variety of prior knowledge to infer community structures. As the problems that network methods try to solve and the network data to be analyzed become increasingly more sophisticated, new approaches have also been proposed and developed, particularly those that utilize deep learning and convert networked data into low dimensional representation. Despite all the recent advancement, there is still a lack of insightful understanding of the theoretical and methodological underpinning of community detection, which will be critically important for future development of the area of network analysis. In this paper, we develop and present a unified architecture of network community-finding methods to characterize the state-of-the-art of the field of community detection. Specifically, we provide a comprehensive review of the existing community detection methods and introduce a new taxonomy that divides the existing methods into two categories, namely probabilistic graphical model and deep learning. We then discuss in detail the main idea behind each method in the two categories. Furthermore, to promote future development of community detection, we release several benchmark datasets from several problem domains and highlight their applications to various network analysis tasks. We conclude with discussions of the challenges of the field and suggestions of possible directions for future research.

Anomalies are rare observations (e.g., data records or events) that deviate significantly from the others in the sample. Over the past few decades, research on anomaly mining has received increasing interests due to the implications of these occurrences in a wide range of disciplines - for instance, security, finance, and medicine. For this reason, anomaly detection, which aims to identify these rare observations, has become one of the most vital tasks in the world and has shown its power in preventing detrimental events, such as financial fraud, network intrusions, and social spam. The detection task is typically solved by identifying outlying data points in the feature space, which, inherently, overlooks the relational information in real-world data. At the same time, graphs have been prevalently used to represent the structural/relational information, which raises thegraph anomaly detection problem- identifying anomalous graph objects (i.e., nodes, edges and sub-graphs) in a single graph, or anomalous graphs in a set/database of graphs. Conventional anomaly detection techniques cannot tackle this problem well because of the complexity of graph data (e.g., irregular structures, relational dependencies, node/edge types/attributes/directions/multiplicities/weights, large scale, etc.). However, thanks to the advent of deep learning in breaking these limitations, graph anomaly detection with deep learning has received a growing attention recently. In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection. Specifically, we provide a taxonomy that follows a task-driven strategy and categorizes existing work according to the anomalous graph objects that they can detect. We especially focus on the challenges in this research area and discuss the key intuitions, technical details as well as relative strengths and weaknesses of various techniques in each category. From the survey results, we highlight 12 future research directions spanning unsolved and emerging problems introduced by graph data, anomaly detection, deep learning and real-world applications. Additionally, to provide a wealth of useful resources for future studies, we have compiled a set of open-source implementations, public datasets, and commonly-used evaluation metrics. With this survey, our goal is to create a “one-stop-shop” that provides a unified understanding of the problem categories and existing approaches, publicly available hands-on resources, and high-impact open challenges for graph anomaly detection using deep learning.

Link prediction has attracted considerable attention. Empiricism and the evolution mechanism based approach are the mainstream methods for link prediction. However, one drawback of such approaches is that they usually ignore the dynamic evolution mechanism of social networks, yet being dynamic is an essential characteristic of a social network that exists in every stage of the networks evolution. In this paper, we address the problem of temporal link prediction and investigate social networks from the time dimension with the purpose of dynamic evolution mechanism capturing. First, we separate a temporal network into a series of snapshots. Then, we propose a triad transition matrix prediction algorithm to learn the change of the distribution of triads among the different snapshots. The learned changes in the distribution of triads can capture the dynamic evolution of the network. With a proposed triad transition influence quantification algorithm, we propose a motifs based link prediction method for temporal link prediction. The proposed method can capture the dynamic evolution of temporal networks and is universal than existing methods. Extensive experiments on disparate real-world networks and model networks with controllable evolution demonstrate the effectiveness of the proposed method.

Community detection on social networks is a fundamental and crucial task in the research field of social computing. Here we proposeDSCPCD—a dual structural consistency preserving community detection method to uncover the hidden community structure, which is designed regarding two criteria: 1) users interact with each other in a manner combining uncertainty and certainty; 2) original explicit network (two linked users are friends) and potential implicit network (two linked users have common friends) should have a consistent community structure, i.e.,dual structural consistency. Particularly,DSCPCDformulates each user in a social network as an individual in an evolutionary game associated with community-aware payoff settings, where the community state evolves under the guidance of replicator dynamics. To further seek each user's membership, we develop ahappinessindex to measure all users’ satisfaction towards two community structures in explicit and implicit networks, meanwhile, the dual community structural consistency between the two networks is also characterized. Specifically, each user is assumed to maximize thehappinessbounded by the evolutionary community state. We evaluateDSCPCDon several real-world and synthetic datasets, and the results show that it can yield substantial performance gains in terms of detection accuracy over several baselines.

Signed network representation is a key problem for signed network data. Previous studies have shown that by preserving multi-order signed proximity (SP), expressive node representations can be learned. However, multi-order SP cannot be perfectly encoded using limited samples extracted from random walks, which reduces effectiveness. To perfectly encode multi-order SP, we have innovatively integrated the informativeness of infinite samples to construct high-level summaries of multi-order SP without explicit sampling. Based on these summaries, we propose a method called SPMF, in which node representations are obtained using low-rank matrix approximation. Furthermore, we theoretically investigate the rationality of SPMF by examining its relationship with a powerful representation learning architecture. In sign inference and link prediction tasks with several real-world datasets, SPMF is empirically competitive compared with state-of-the-art methods. Additionally, two tricks are designed for improving the scalability of SPMF. One trick aims to filter out less informative summaries, and another one is inspired by kernel techniques. Both tricks empirically improve scalability while preserving effective performance. The code for our methods is publicly available.

Graph Neural Networks (GNNs) have yielded fruitful results in learning multi-view graph data. However, it is challenging for existing GNNs to capture the potential correlation information (PCI) among the graph structure features of multiple views. It is also challenging to adaptively identify valuable neighbors for node feature fusion in different views. To this end, we propose a novelReinforcedTensorGraphNeuralNetwork (RTGNN) framework to more effectively perform multi-view graph representation learning through reinforcing inter- and intra-graph aggregation. Specifically, RTGNN first uses tensor decomposition to extract the graph structure features (GSFs) of each view in the common feature space. These GSFs contain the PCI of multiple views and alleviate fusion conflicts that may be caused by differences between view feature spaces in cross-view feature fusion. Since fusing the features of all neighbor nodes may harm the features of the center node, we filter the irrelevant neighbors to improve the performance of intra-graph aggregation in each view. Concretely, a reinforcement learning (RL)-guided scheme is developed to automatically calculate the optimal filtering threshold for each view, avoiding tedious manual updates and infeasible back propagation updates. Experimental results and analysis on five datasets show that RTGNN surpasses the best multi-view graph representation baselines and achieves the maximum 14.26% performance improvement in terms of F1. The code link ishttps://github.com/RingBDStack/RTGNN.

Visual tracking is a visual task that tracks a specific target by only giving its first frame location and size. To punish the low-quality but high-scoring tracking results, researchers resorted to foreground reinforcement learning to suppress the scores of positive samples near edges. However, for training with negative samples, all backgrounds are equally labeled as false. In this way, the interdependence and difference between the foreground and the background are not considered. We interpret the underlying reason for drifts as the imbalance between the embedding of background and foreground information. Specifically, some catastrophic tracking results and common tracking errors should not be treated equally but should strengthen the implicit connection between the foreground and background. In this paper, we propose a Mutual Attention (MA) module to strengthen the interdependence between positive and negative samples. It can aggregate the rich contextual interdependence between the target template and the search area, thereby providing an implicit way to update the target template accordingly. As for the difference, we design a background training enhancement (BTE) mechanism to distinguish negative samples with varying degrees of error, that is, to down-weight outrageous and absurd tracking results to improve the robustness of the tracker. The results on a large number of benchmarks indicate the validity of our results, such as OTB-100, VOT-2018, VOT-2019, and LaSOT.

Classification methods for streaming data are not new, but very few current frameworks address all three of the most common problems with these tasks: concept drift, noise, and the exorbitant costs associated with labeling the unlabeled instances in data streams. Motivated by this gap in the field, we developed an active learning framework based on a dual-query strategy and Ebbinghaus's law of human memory cognition. Called CogDQS, the query strategy samples only the most representative instances for manual annotation based on local density and uncertainty, thus significantly reducing the cost of labeling. The policy for discerning drift from noise and replacing outdated instances with new concepts is based on the three criteria of the Ebbinghaus forgetting curve: recall, the fading period, and the memory strength. Simulations comparing CogDQS with baselines on six different data streams containing gradual drift or abrupt drift with and without noise show that our approach produces accurate, stable models with good generalization ability at minimal labeling, storage, and computation costs.

Trust prediction provides valuable support for decision making, information dissemination, and product promotion in online social networks. As a complex concept in the social network community, trust relationships among people can be established virtually based on: 1) their interaction behaviors, e.g., the ratings and comments that they provided; 2) the contextual information associated with their interactions, e.g., location and culture; and 3) the relative temporal features of interactions and the time periods when the trust relationships hold. Most of the existing works only focus on some aspects of trust, and there is not a comprehensive study of user trust development that considers and incorporates 1)-3) in trust prediction. In this article, we propose a context-aware deep trust prediction model C-DeepTrust to fill this gap. First, we conduct user feature modeling to obtain the user's static and dynamic preference features in each context. Static user preference features are obtained from all the ratings and reviews that a user provided, while dynamic user preference features are obtained from the items rated/reviewed by the user in time series. The obtained context-aware user features are then combined and fed into the multilayer projection structure to further mine the context-aware latent features. Finally, the context-aware trust relationships between users are calculated by their context-aware feature vector cosine similarities according to the social homophily theory, which shows a pervasive property of social networks that trust relationships are more likely to be developed among similar people. Extensive experiments conducted on two real-world datasets show the superior performance of our approach compared with the representative baseline methods.

Tourism is an important industry and a popular entertainment activity involving billions of visitors per annum. One challenging problem tourists face is identifying satisfactory products from vast tourism information. Most of travel recommendation methods regard the recommendation procedure as a static process and only focus on immediate rewards. Meanwhile, they often infer user intensions from click behaviors and ignore the informative keywords of the clicked products. To this end, in this article, we present a Keywords-enhanced Deep Reinforcement Learning model (KDRL) framework. Specifically, we formalize travel recommendation as a Markov Decision Process and implement it upon the Actor–Critic framework. It integrates keyword information into the reinforcement learning–(RL) based recommendation framework by devising novel state representation and reward function and learns the travel recommendation and keywords generation simultaneously. To the best of our knowledge, this is the first time that keywords are explicitly discussed and used in RL-based travel recommendations. Extensive experiments are performed on the real-world datasets and the results clearly show the superior performance of KDRL compared with the baseline methods.

No abstract available.

Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real-world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL is the first attempt to advance the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of the proposed VIB-GSL.

State-of-the-art Graph Neural Networks (GNNs) have achieved tremendous success in social event detection tasks when restricted to a closed set of events. However, considering the large amount of data needed for training and the limited ability of a neural network in handling previously unknown data, it is hard for existing GNN-based methods to operate in an open set setting. To address this problem, we design a Quality-aware Self-improving Graph Neural Network (QSGNN) which extends the knowledge from known to unknown by leveraging the best of known samples and reliable knowledge transfer. Specifically, to fully exploit the labeled data, we propose a novel supervised pairwise loss with an additional orthogonal inter-class relation constraint to train the backbone GNN encoder. The learnt, already-known events further serve as strong reference bases for the unknown ones, which greatly prompts knowledge acquisition and transfer. When the model is generalized to unknown data, to ensure the effectiveness and reliability, we further leverage the reference similarity distribution vectors for pseudo pairwise label generation, selection and quality assessment. Following the diversity principle of active learning, our method selects diverse pair samples with the generated pseudo labels to fine-tune the GNN encoder. Besides, we propose a novel quality-guided optimization in which the contributions of pseudo labels are weighted based on consistency. Experimental results validate that our model achieves state-of-the-art results and extends well to unknown events.

Integrating multiple online social networks (OSNs) has important implications for many downstream social mining tasks, such as user preference modelling, recommendation, and link prediction. However, it is unfortunately accompanied by growing privacy concerns about leaking sensitive user information. How to fully utilize the data from different online social networks while preserving user privacy remains largely unsolved. To this end, we propose a Cross-network Social User Embedding framework, namely DP-CroSUE, to learn the comprehensive representations of users in a privacy-preserving way. We jointly consider information from partially aligned social networks with differential privacy guarantees. In particular, for each heterogeneous social network, we first introduce a hybrid differential privacy notion to capture the variation of privacy expectations for heterogeneous data types. Next, to find user linkages across social networks, we make unsupervised user embedding-based alignment in which the user embeddings are achieved by the heterogeneous network embedding technology. To further enhance user embeddings, a novel cross-network GCN embedding model is designed to transfer knowledge across networks through those aligned users. Extensive experiments on three real-world datasets demonstrate that our approach makes a significant improvement on user interest prediction tasks as well as defending user attribute inference attacks from embedding.

DBSCAN is widely used in many scientific and engineering fields because of its simplicity and practicality. However, due to its high sensitivity parameters, the accuracy of the clustering result depends heavily on practical experience. In this paper, we first propose a novel Deep Reinforcement Learning guided automatic DBSCAN parameters search framework, namely DRL-DBSCAN. The framework models the process of adjusting the parameter search direction by perceiving the clustering environment as a Markov decision process, which aims to find the best clustering parameters without manual assistance. DRL-DBSCAN learns the optimal clustering parameter search policy for different feature distributions via interacting with the clusters, using a weakly-supervised reward training policy network. In addition, we also present a recursive search mechanism driven by the scale of the data to efficiently and controllably process large parameter spaces. Extensive experiments are conducted on five artificial and real-world datasets based on the proposed four working modes. The results of offline and online tasks show that the DRL-DBSCAN not only consistently improves DBSCAN clustering accuracy by up to 26% and 25% respectively, but also can stably find the dominant parameters with high computational efficiency. The code is available at https://github.com/RingBDStack/DRL-DBSCAN.

Graph anomaly detection in this paper aims to distinguish abnormal nodes that behave differently from the benign ones accounting for the majority of graph-structured instances. Receiving increasing attention from both academia and industry, yet existing research on this task still suffers from two critical issues when learning informative anomalous behavior from graph data. For one thing, anomalies are usually hard to capture because of their subtle abnormal behavior and the shortage of background knowledge about them, which causes severe anomalous sample scarcity. Meanwhile, the overwhelming majority of objects in real-world graphs are normal, bringing the class imbalance problem as well. To bridge the gaps, this paper devises a novel Data Augmentation-based Graph Anomaly Detection (DAGAD) framework for attributed graphs, equipped with three specially designed modules: 1) an information fusion module employing graph neural network encoders to learn representations, 2) a graph data augmentation module that fertilizes the training set with generated samples, and 3) an imbalance-tailored learning module to discriminate the distributions of the minority (anomalous) and majority (normal) classes. A series of experiments on three datasets prove that DAGAD outperforms ten state-of-the-art baseline detectors concerning various mostly-used metrics, together with an extensive ablation study validating the strength of our proposed modules.

Fact-checking is vital for countering fake news. This process requires verifying the truthfulness of a claim by reasoning about multiple pieces of evidence. The current dominant approach depends upon capturing the claim-evidence relations from a claim-evidence interaction graph. Existing solutions utilize phrase-level semantics on a single-granularity but ignore other hierarchical features, such as fact- and sentence-level textual semantics and their logical topology. Since the hierarchical features often provide hints to infer collaborative high-order clues that can be essential for fact-checking, they should not be overlooked. This paper proposes a better method to model the claim-evidence graph in a multi-granularity manner. Doing so allows one to exploit more textual semantics and logical topology between a claim and its evidence. To achieve the target, we first employ a graph inference learning framework to infer graph nodes on different granular semantic units within their hierarchical topology. Then, an inference learning procedure is designed to optimize the global textual similarity and local topological reachability from the claim-evidence graph. We evaluate our approach by applying it to fact-checking on an open dataset, and experimental results show that our technique outperforms existing graph-based techniques by a large margin.

Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.

The popularity of social platforms has attracted lots of studies on mining social media data, especially on mining social events. Social event detection, due to its wide applications, has now become a trivial task. Existing approaches exploiting Graph Neural Networks (GNNs) usually follow a two-step strategy: 1) constructing text graphs based on various views (co-user, co-entities and co-hashtags); and 2) learning a unified text representation by a specific GNN model. Generally, the results heavily rely on the quality of the constructed graphs and the specific message passing scheme. However, existing methods have deficiencies in both aspects: 1) They fail to recognize the noisy information induced by unreliable views. 2) Temporal information which works as a vital indicator of events is neglected in most works. To solve these two problems, we propose ETGNN, a novel Evidential Temporal-aware Graph Neural Network. Specifically, we construct view-specific graphs whose nodes are the texts and edges are determined by several types of shared elements respectively. To incorporate temporal information into the message passing scheme, we introduce a novel temporal-aware aggregator which assigns weights to neighbours according to an adaptive time exponential decay formula. Considering the view-specific uncertainty, the representations of all views are converted into mass functions through evidential deep learning (EDL) neural networks, and further combined via Dempster-Shafer theory (DST) to make the final detection. Experiments on three real-world events datasets validate that ETGNN gets accurate, reliable and robust results in social event detection.

Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes. High-performance GNN models always depend on both rich features and complete edge information in graph. However, such information could possibly be isolated by different data holders in practice, which is the so-called data isolation problem. To solve this problem, in this paper, we propose VFGNN, a federated GNN learning paradigm for privacy-preserving node classification task under data vertically partitioned setting, which can be generalized to existing GNN models. Specifically, we split the computation graph into two parts. We leave the private data (i.e., features, edges, and labels) related computations on data holders, and delegate the rest of computations to a semi-honest server. We also propose to apply differential privacy to prevent potential information leakage from the server. We conduct experiments on three benchmarks and the results demonstrate the effectiveness of VFGNN.

Graph-level anomaly detection aims to distinguish anomalous graphs in a graph dataset from normal graphs. Anomalous graphs represent a very few but essential patterns in the real world. The anomalous property of a graph may be referable to its anomalous attributes of particular nodes and anomalous substructures that refer to a subset of nodes and edges in the graph. In addition, due to the imbalance nature of anomaly problem, anomalous information will be diluted by normal graphs with overwhelming quantities. Various anomaly notions in the attributes and/or substructures and the imbalance nature together make detecting anomalous graphs a non-trivial task. In this paper, we propose a graph neural network for graph-level anomaly detection, namely iGAD. Specifically, an anomalous graph attribute-aware graph convolution and an anomalous graph substructure-aware deep Random Walk Kernel (deep RWK) are welded into a graph neural network to achieve the dual-discriminative ability on anomalous attributes and substructures. Deep RWK in iGAD makes up for the deficiency of graph convolution in distinguishing structural information caused by the simple neighborhood aggregation mechanism. Further, we propose a Point Mutual Information (PMI)-based loss function to target the problems caused by imbalance distributions. PMI-based loss function enables iGAD to capture essential correlation between input graphs and their anomalous/normal properties. We evaluate iGAD on four real-world graph datasets. Extensive experiments demonstrate the superiority of iGAD on the graph-level anomaly detection task.

This paper demonstrates Fair-SRS, a Fair Session-based Recommendation System that predicts user's next click based on their historical and current sessions. Fair-SRS provides personalized and diversified recommendations in two main steps: (1) forming user's session graph embeddings based on their long- and short-term interests, and (2) computing user's level of interest in diversity based on their recently-clicked items' similarity. In real-world scenarios, users tend to interact with more or fewer contents at different times, and providers expect to receive more exposure for their items. To achieve the objectives of both sides, the proposed Fair-SRS optimizes recommendations by making a trade-off between accuracy and personalized diversity.

Graph anomaly detection, here, aims to find rare patterns that are significantly different from other nodes. Attributed graphs containing complex structure and attribute information are ubiquitous in our life scenarios such as bank account transaction graph and paper citation graph. Anomalous nodes on attributed graphs show great difference from others in the perspectives of structure and attributes, and give rise to various types of graph anomalies. In this paper, we investigate three types of graph anomalies: local, global, and structure anomalies. And, graph neural networks (GNNs) based anomaly detection methods attract considerable research interests due to the power of modeling attributed graphs. However, the convolution operation of GNNs aggregates neighbors information to represent nodes, which makes node representations more similar and cannot effectively distinguish between normal and anomalous nodes, thus result in sub-optimal results. To improve the performance of anomaly detection, we propose a novel community-aware attributed graph anomaly detection framework (ComGA). We design a tailored deep graph convolutional network (tGCN) to anomaly detection on attributed graphs. Extensive experiments on eight real-life graph datasets demonstrate the effectiveness of ComGA.

Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space, leading to the information loss of topological properties (e.g. hierarchy and circularity). Moreover, due to the topological heterogeneity (i.e., different densities across the graph structure) of graph data, they suffer from serious topological distortion problems. In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. To better preserve the topological properties, we approximate the discrete structure as a continuous Riemannian geometric manifold and generate negative samples efficiently from the wrapped normal distribution. To deal with the topological heterogeneity, we leverage the Ricci curvature for local structures with different topological properties, obtaining to low-distortion representations. Extensive experiments show that CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks and shows superior robustness and generalization.

In the fraud graph, fraudsters often interact with a large number of benign entities to hide themselves. So, there are not only the homophilic connections formed by the same label nodes (similar nodes), but also the heterophilic connections formed by the different label nodes (dissimilar nodes). However, the existing GNN-based fraud detection methods just enhance the homophily in fraud graph and use the low-pass filter to retain the commonality of node features among the neighbors, which inevitably ignore the difference among neighbor of heterophilic connections. To address this problem, we propose a Graph Neural Network-based Fraud Detector with Homophilic and Heterophilic Interactions (H2-FDetector for short). Firstly, we identify the homophilic and heterophilic connections with the supervision of labeled nodes. Next, we design a new information aggregation strategy to make the homophilic connections propagate similar information and the heterophilic connections propagate difference information. Finally, a prototype prior is introduced to guide the identification of fraudsters. Extensive experiments on two real public benchmark fraud detection tasks demonstrate that our method apparently outperforms state-of-the-art baselines.

Signed network embedding (SNE) has received considerable attention in recent years. A mainstream idea of SNE is to learn node representations by estimating the ratio of sampling densities. Though achieving promising performance, these methods based on density ratio estimation are limited to the issues of confusing sample, expected error, and fixed priori. To alleviate the above-mentioned issues, in this paper, we propose a novel dual-branch density ratio estimation (DDRE) architecture for SNE. Specifically, DDRE 1) consists of a dual-branch network, dealing with the confusing sample; 2) proposes the expected matrix factorization without sampling to avoid the expected error; and 3) devises an adaptive cross noise sampling to alleviate the fixed priori. We perform sign prediction and node classification experiments on four real-world and three artificial datasets, respectively. Extensive empirical results demonstrate that DDRE not only significantly outperforms the methods based on density ratio estimation but also achieves competitive performance compared with other types of methods such as graph likelihood, generative adversarial networks, and graph convolutional networks. Code is publicly available at https://github.com/WHU-SNA/DDRE.

Event extraction is a ftask for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an argument’s role often varies in different contexts. While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches. This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We achieve this through a carefully designed task-oriented dialogue system. To model the argument relation, we employ reinforcement learning and incremental learning to extract multiple arguments via a multi-turned, iterative process. Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually. It then uses the newly obtained information to improve the decisions of previously extracted arguments. This two-way feedback process allows us to exploit the argument relations to effectively settle argument roles, leading to better sentence understanding and event extraction. Experimental results show that our approach consistently outperforms seven state-of-the-art event extraction methods for the classification of events and argument role and argument identification.

Brain electroencephalography (EEG), the complex, weak, multivariate, nonlinear, and nonstationary time series, has been recently widely applied in neurocognitive disorder diagnoses and brain-machine interface developments. With its specific features, unlabeled EEG is not well addressed by conventional unsupervised time-series learning methods. In this article, we handle the problem of unlabeled EEG time-series clustering and propose a novel EEG clustering algorithm, that we call mwcEEGc. The idea is to map the EEG clustering to the maximum-weight clique (MWC) searching in an improved Fréchet similarity-weighted EEG graph. The mwcEEGc considers the weights of both vertices and edges in the constructed EEG graph and clusters EEG based on their similarity weights instead of calculating the cluster centroids. To the best of our knowledge, it is the first attempt to cluster unlabeled EEG trials using MWC searching. The mwcEEGc achieves high-quality clusters with respect to intracluster compactness as well as intercluster scatter. We demonstrate the superiority of mwcEEGc over ten state-of-the-art unsupervised learning/clustering approaches by conducting detailed experimentations with the standard clustering validity criteria on 14 real-world brain EEG datasets. We also present that mwcEEGc satisfies the theoretical properties of clustering, such as richness, consistency, and order independence.

Quantum blockchain is expected to offer an alternative to classical blockchain to resist malicious attacks laughed by future quantum computers. Although a few quantum blockchain schemes have been constructed, their efficiency is low and unable to meet application requirements due to the fact that they lack of a suitable consensus mechanism. To tackle this issue, a consensus mechanism called quantum delegated proof of stake (QDPoS) is constructed by using quantum voting to provide fast decentralization for the quantum blockchain scheme at first. Then an efficient scheme is proposed for quantum blockchain based on QDPoS, where the classical information is initialized as a part of each single quantum state and these quantum states are entangled to form the chain. Compared with previous methods, the designed quantum blockchain scheme is more complete and carried out with higher efficiency, which greatly contributes to better adapting to the challenges of the quantum era.

Cities are becoming smarter because of recent advances in artificial intelligence and the Internet of Things. However, heterogeneous data source in smart cities are continuously producing low-quality data, and ever-growing applications have greater real-time requirements. Therefore, this article proposes a data stream cleaning system (named DSCS) using edge intelligence to utilize the advantages of cloud servers and edge devices. The DSCS in edge nodes consists of a dynamic protocol interpreter, a structure parser, and a cleaning model activator. Meanwhile, a cloud server, which has pools of protocol and structured programs and cleaning models, supports the edge nodes to adapt massive heterogeneous data sources. To validate the proposed data cleaning system, we applied it to two scenarios: monitoring the injection molding machines, and base stations. The DSCS can have a stable processing time when the number of accessed edge devices is increased, as well as a good cleaning effect.

Currently, electroencephalogram (EEG) is mostly analyzed in a supervised way, which requires EEG labels (e.g., EEG classification). With the ever-increasing amount of unlabeled/mislabeled EEG in neuropsychiatric disorder diagnosis, BCI, and rehabilitation, manually labeling of EEG data is a labor intensive and time-consuming process, and few labs have developed algorithms to analyze EEG in an unsupervised manner (i.e., EEG clustering). In this paper, we propose a cooperative game inspired approach to cluster multi-trial EEG data. The idea is to map multi-trial EEG clustering to the coalition formation in a cooperative game, and then identify cluster center (the EEG trial with highest Shapley value) and assign EEG trials into proper clusters based on their cross correlation-transformed Shapley values. We demonstrate the mapped EEG cooperative game is convex, and it leads to an algorithm for multi-trial EEG clustering named CoGEEGc. The CoGEEGc yields high-quality multi-trial EEG clustering with respect to intra-cluster compactness and inter-cluster scatter. We show that CoGEEGc outperforms 15 state-of-the-art EEG or time series clustering approaches through detailed experimentation on real-world multi-trial EEG datasets. Comparison against 15 methods with four theoretical properties of clustering further illustrates the superiority of CoGEEGc, as it satisfies two properties while other approaches only satisfy one.

Many studies focusing on integrating reviews with ratings to improve recommendation performance have been quite successful. However, these works still face several shortcomings: (1) The importance of dynamically integrating review and interaction data features is typically ignored, yet treating these fusion features equally may lead to an incomplete understanding of user preferences. (2) Some forms of soft attention methods are adopted to model the local semantic information of words. As features thus captured may contain irrelevant information, the generated attention map is neither discriminatory nor detailed. In this paper, we propose a novelAdaptiveHierarchicalAttention-enhancedGated network integrating reviews for item recommendation, named AHAG. AHAG is a unified framework to capture the hidden intentions of users by adaptively incorporating reviews. Specifically, we design a gated network to dynamically fuse the extracted features and select the features that are most relevant to user preferences. To capture distinguishing fine-grained features, we introduce a hierarchical attention mechanism to learn important semantic information features and the dynamic interaction of these features. Besides, the high-order non-linear interaction of neural factorization machines is utilized to derive the rating prediction. Experiments on seven real-world datasets show that the proposed AHAG significantly outperforms state-of-the-art methods. Furthermore, the attention mechanism can highlight the relevant information in reviews to increase the interpretability of the recommendation task. Source codes are available inhttps://github.com/luojia527/AHAG.

Object tracking is an essential and challenging sub-domain in the field of computer vision owing to its wide range of applications and complexities of real-life situations. It has been studied extensively over the last decade, leading to the proposal of several tracking frameworks and approaches. Recently, the introduction of reinforcement learning and the ‘Actor-Critic’ framework has effectively improved the tracking speed of deep learning trackers. However, most existing deep reinforcement learning trackers experience a slight performance degradation mainly owing to the drift issues. Drifts pose a threat to the tracking performance, which may lead to losing the tracked target. Herein, we propose a drift-proof tracker with deep reinforcement learning that aims to improve the tracking performance by counteracting drifts while maintaining its real-time advantage. We utilize a reward function with the Distance-IoU (DIoU) metric to guide the reinforcement learning to alleviate the drifts caused by the trained model. Furthermore, double negative samples (hard negative and drift samples) are constructed in tracking for network initialization, which is followed by calculating the loss by a small error-friendly loss function. Therefore, our tracker can better discriminate between the positive and negative samples and correct the predicted bounding boxes when the drift occurs. Meanwhile, a generative adversarial network is adopted for positive sample augmentation. Extensive experimental results on multiple popular benchmarks show that our algorithm effectively reduces the occurrences of drift and boosts the tracking performance, compared to those of other state-of-the-art trackers.

With the development of e-commerce, fraud behaviors have been becoming one of the biggest threats to the e-commerce business. Fraud behaviors seriously damage the ranking system of e-commerce platforms and adversely influence the shopping experience of users. It is of great practical value to detect fraud behaviors on e-commerce platforms. However, the task is non-trivial, since the adversarial action taken by fraudsters. Existing fraud detection systems used in the e-commerce industry easily suffer from performance decay and can not adapt to the upgrade of fraud patterns, as they take already known fraud behaviors as supervision information to detect other suspicious behaviors. In this article, we propose a competitive graph neural networks (CGNN)-based fraud detection system (eFraudCom) to detect fraud behaviors at one of the largest e-commerce platforms, “Taobao” 1 . In the eFraudCom system, (1) the competitive graph neural networks (CGNN) as the core part of eFraudCom can classify behaviors of users directly by modeling the distributions of normal and fraud behaviors separately; (2) some normal behaviors will be utilized as weak supervision information to guide the CGNN to build the profile for normal behaviors that are more stable than fraud behaviors. The algorithm dependency on fraud behaviors will be eliminated, which enables eFraudCom to detect fraud behaviors in presence of the new fraud patterns; (3) the mutual information regularization term can maximize the separability between normal and fraud behaviors to further improve CGNN. eFraudCom is implemented into a prototype system and the performance of the system is evaluated by extensive experiments. The experiments on two Taobao and two public datasets demonstrate that the proposed deep framework CGNN is superior to other baselines in detecting fraud behaviors. A case study on Taobao datasets verifies that CGNN is still robust when the fraud patterns have been upgraded.

Graph-based algorithms have drawn much attention thanks to their impressive success in semi-supervised setups. For better model performance, previous studies have learned to transform the topology of the input graph. However, these works only focus on optimizing the original nodes and edges, leaving the direction of augmenting existing data insufficiently explored. In this paper, we propose a novel heuristic pre-processing technique, namelyLocal Label Consistency Strengthening (ŁLCS), which automatically expands new nodes and edges to refine the label consistency within a dense subgraph. Our framework can effectively benefit downstream models by substantially enlarging the original training set with high-quality generated labeled data and refining the original graph topology. To justify the generality and practicality of ŁLCS, we couple it with the popular graph convolution network and graph attention network to perform extensive evaluations on three standard datasets. In all setups tested, our method boosts the average accuracy by a large margin of 4.7% and consistently outperforms the state-of-the-art.

Adaptive traffic signal control plays a significant role in the construction of smart cities. This task is challenging because of many essential factors, such as cooperation among neighboring intersections and dynamic traffic scenarios. First, to facilitate the cooperation of traffic signals, existing work adopts graph neural networks to incorporate the temporal and spatial influences of the surrounding intersections into the target intersection, where spatial-temporal information is used separately. However, one drawback of these methods is that the spatial-temporal correlations are not adequately exploited to obtain a better control scheme. Second, in a dynamic traffic environment, the historical state of the intersection is also critical for predicting future signal switching. Previous work mainly solves this problem using the current intersection's state, neglecting the fact that traffic flow is continuously changing both spatially and temporally and does not handle the historical state.

Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks. Most existing GNNs embed graph data into Euclidean space and thus are less effective to capture the ubiquitous hierarchical structures in real-world networks. Hyperbolic Graph Neural Networks (HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning. In hyperbolic geometry, the graph hierarchical structure can be reflected by the curvatures of the hyperbolic space, and different curvatures can model different hierarchical structures of a graph. However, most existing HGNNs manually set the curvature to a fixed value for simplicity, which achieves a suboptimal performance of graph learning due to the complex and diverse hierarchical structures of the graphs. To resolve this problem, we propose an Adaptive Curvature Exploration Hyperbolic Graph Neural Network named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Specifically, ACE-HGNN exploits a multi-agent reinforcement learning framework and contains two agents, ACE-Agent and HGNN-Agent for learning the curvature and node representations, respectively. The two agents are updated by a Nash Q-leaning algorithm collaboratively, seeking the optimal hyperbolic space indexed by the curvature. Extensive experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.

Multivariate Hawkes processes (MHPs) are classic methods to learn temporal patterns in event sequences of different entities. Traditional MHPs with explicit parametric intensity functions are friendly to model interpretability. However, recent Deep MHPs which employ various variants of recurrent neural networks are hardly to understand, albeit more expressive towards event sequences. The lack of model interpretability of Deep MHPs leads to a limited comprehension of complicated dynamics between events. To this end, we present a new Disentangled Deep Multivariate Hawkes Process $(\mathrm{D}^{2}$ MHP) to enhance model expressiveness and meanwhile maintain model interpretability. $\mathrm{D}^{2}$ MHP achieves state disentanglement by disentangling the latent representation of an event sequence into static and dynamic latent variables, and matches these latent variables to interpretable factors in the intensity function. Moreover, considering that an entity typically has multiple identities, $\mathrm{D}^{2}$ MHP further splits these latent variables into factorized representations, each of which is associated with a corresponding identity. Experiments on real-world datasets show that $\mathrm{D}^{2}$ MHP yields significant and consistent improvements over state-of-the-art baselines. We also demonstrate model interpretability via the detailed analysis.

The objective of fraud detection is to distinguish fraudsters from normal users. In graph/network environments, both fraudsters and normal users are modeled as nodes, and the connections between those nodes are represented as edges. Fraudsters typically try to camouflage themselves with “normal” behaviors, say, by deliberately establishing many connections to normal users. Such camouflage inherently makes their appearance inconsistent with the essence of what it is to be normal, and gives rise to inconsistencies in the graph. In this paper, we investigate three aspects of these graph inconsistencies: features, topologies, and relations. To date, graph-based fraud detectors have shown a rather limited capability to fuse information about different types of inconsistencies. Apart from that, there is another problem of imbalance to overcome. This is because fraudsters usually only account for a very small percentage of all users. To achieve a promising capability, i.e., dual-resistant to graph inconsistency and imbalance, we present a new fraud detection model FRAUDRE based on Graph Neural Networks. Extensive experiments comparing eight up-to-date baselines on two real-world datasets, Amazon and YelpChi, demonstrate the superiority of FRAUDRE.

A redundancy-based strategy is widely employed by assigning each task to multiple workers and then inferring the correct answer (called truth) for each task in crowdsourcing. Most existing truth inference methods are designed for the situation with a fairly big number of answers for each task (referred to as high redundancy). However, the high redundancy unavoidably leads to a high cost. In this work, we propose a novel truth inference approach called TWLR based on worker representations for the situation with a small number of answers for each task (referred to as low redundancy). We develop a deep model to learn the representations of workers considering both answers and worker-task relations. For each task, we identify the worker with the highest quality, and select his/her answer as the predicted answer. To the best of our knowledge, this is the first work to perform truth inference by utilizing deep learning techniques to deal with the low redundancy situation in crowdsourcing. We have conducted a set of experiments against 7 real-world datasets to show the accuracy improvement of our truth inference approach by comparing with 11 baseline methods.

Crowdsourcing platforms are widely used for requesters to find workers for general tasks. The answers to general tasks are usually open and not constrained by multiple choices. For the general tasks, the worker performance prediction models can facilitate the task assignment process in crowdsourcing. Worker performance prediction is affected by the three roles: the worker, the requester, and the task. The existing worker performance prediction models mainly consider the features of tasks and workers. However, these models rarely consider the features of requesters. And the existing worker performance prediction models for multiple-choice tasks are not suitable for general tasks as they are built based on the workers' accuracy on choices. In this work, we propose a worker performance prediction model by taking account of features of workers, tasks, and requesters to help requesters select workers for their general tasks on crowdsourcing platforms. We design a relationship learning module to learn the low dimension relationship representations of workers, tasks, and requesters. Furthermore, we design a performance learning model to predict workers' performance based on the features and relationship representations of workers, tasks, and requesters. A set of experiments against the realworld dataset from the Zhubajie platform has been conducted. Experimental results show that the proposed approach has better prediction results than the existing baseline methods.

Social events provide valuable insights into group social behaviors and public concerns and therefore have many applications in fields such as product recommendation and crisis management. The complexity and streaming nature of social messages make it appealing to address social event detection in an incremental learning setting, where acquiring, preserving, and extending knowledge are major concerns. Most existing methods, including those based on incremental clustering and community detection, learn limited amounts of knowledge as they ignore the rich semantics and structural information contained in social data. Moreover, they cannot memorize previously acquired knowledge. In this paper, we propose a novel Knowledge-Preserving Incremental Heterogeneous Graph Neural Network (KPGNN) for incremental social event detection. To acquire more knowledge, KPGNN models complex social messages into unified social graphs to facilitate data utilization and explores the expressive power of GNNs for knowledge extraction. To continuously adapt to the incoming data, KPGNN adopts contrastive loss terms that cope with a changing number of event classes. It also leverages the inductive learning ability of GNNs to efficiently detect events and extends its knowledge from previously unseen data. To deal with large social streams, KPGNN adopts a mini-batch subgraph sampling strategy for scalable training, and periodically removes obsolete data to maintain a dynamic embedding space. KPGNN requires no feature engineering and has few hyperparameters to tune. Extensive experiment results demonstrate the superiority of KPGNN over various baselines.

User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited. Recent studies seek to address this challenge from the perspective of meta learning, and most of them follow a manner of parameter initialization, where the model parameters can be learned by a few steps of gradient updates. While these gradient-based meta-learning models achieve promising performances to some extent, a fundamental problem of them is how to adapt the global knowledge learned from previous tasks for the recommendations of cold-start users more effectively.

Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substructures’ semantics, and suffering from interpretation enigmas. This paper presents a novel hierarchical subgraph-level selection and embedding-based graph neural network for graph classification, namely SUGAR, to learn more discriminative subgraph representations and respond in an explanatory way. SUGAR reconstructs a sketched graph by extracting striking subgraphs as the representative part of the original graph to reveal subgraph-level patterns. To adaptively select striking subgraphs without prior knowledge, we develop a reinforcement pooling mechanism, which improves the generalization ability of the model. To differentiate subgraph representations among graphs, we present a self-supervised mutual information mechanism to encourage subgraph embedding to be mindful of the global graph structural properties by maximizing their mutual information. Extensive experiments on six typical bioinformatics datasets demonstrate a significant and consistent improvement in model quality with competitive performance and interpretability.

Smart city communication networks hold the promise of harnessing the Internet of Things, smart devices, intelligent energy grids, autonomous cars, and many other data architectures to improve quality of life for every citizen. As time and progress have gradually shifted this concept from an idea into a reality, the possibilities for what services a smart city might provide have exploded. Along with that expansion, the number of devices that may need to be supported across a communications network has multiplied enormously. However, existing congestion control protocols are not equipped to support this higher requirement for network performance. New protocols are needed to provide higher data throughputs, reduce queuing delays and packet loss, and maintain stable and reliable communications pathways. The end-to-end congestion control protocol presented in this article does all these things. Called high throughput congestion control (HTCC), the framework takes full advantage of reinforcement learning and a fast growth algorithm to adaptively control the bytes in flight across the network's links to suit the prevailing network conditions. The result is a protocol that not only finds the optimal tradeoff between throughput, latency, and packet loss, but also significantly speeds up the learning process to avoid wasting network resources, use all free bandwidth and maximize network utilization. A comprehensive set of experiments with HTCC and six state-of-the-art protocols-Copa, PCC Vivace, PCC-Allegro, TCP Cubic, TaoVA-100x, and FillP-Sheep-demonstrate that, in most conditions, HTCC is able to make the best tradeoff between throughput, delay, and loss rate.

Vehicular ad hoc networks ( VANETs ) and the services they support are an essential part of intelligent transportation. Through physical technologies, applications, protocols, and standards, they help to ensure traffic moves efficiently and vehicles operate safely. This article surveys the current state of play in VANETs development. The summarized and classified include the key technologies critical to the field, the resource-management and safety applications needed for smooth operations, the communications and data transmission protocols that support networking, and the theoretical and environmental constructs underpinning research and development, such as graph neural networks and the Internet of Things. Additionally, we identify and discuss several challenges facing VANETs, including poor safety, poor reliability, non-uniform standards, and low intelligence levels. Finally, we touch on hot technologies and techniques, such as reinforcement learning and 5G communications, to provide an outlook for the future of intelligent transportation systems.

The merging boundaries between edge computing and deep learning are forging a new blueprint for the Internet of Things (IoT). However, the low-quality of data in many IoT platforms, especially those composed of heterogeneous devices, is hindering the development of high-quality applications for those platforms. The solution presented in this article is intelligent data collaboration, i.e., the concept of deep learning providing IoT with the ability to adaptively collaborate to accomplish a task. Here, we outline the concept of intelligent data collaboration in detail and present a mathematical model in general form. To demonstrate one possible case where intelligent data collaboration would be useful, we prepared an implementation called adaptive data cleaning (ADC), designed to filter noisy data out of temperature readings in an IoT base station network. ADC primarily consists of a denoising autoencoder LSTM for predictions and a four-level data processing mechanism to perform the filtering. Comparisons between ADC and a maximum slop method show ADC with the lowest false error and the best filtering rates.

Temporal network embedding, which aims to learn the low-dimensional representations of nodes in temporal networks that can capture and preserve the network structure and evolution pattern, has attracted much attention from the scientific community. However, existing methods suffer from two main disadvantages: 1) they cannot preserve the node temporal proximity that capture important properties of the network structure; and 2) they cannot represent the nonlinear structure of temporal networks. In this paper, we propose a high-order nonlinear information preserving (HNIP) embedding method to address these issues. Specifically, we define three orders of temporal proximities by exploring network historical information with a time exponential decay model to quantify the temporal proximity between nodes. Then, we propose a novel deep guided auto-encoder to capture the highly nonlinear structure. Meanwhile, the training set of the guide auto-encoder is generated by the temporal random walk (TRW) algorithm. By training the proposed deep guided auto-encoder with a specific mini-batch stochastic gradient descent algorithm, HNIP can efficiently preserves the temporal proximities and highly nonlinear structure of temporal networks. Experimental results on four real-world networks demonstrate the effectiveness of the proposed method.

Knowledge-graph-aware recommendation systems have increasingly attracted attention in both industry and academic recently. Many existing knowledge-aware recommendation methods have achieved better performance, which usually perform recommendation by reasoning on the paths between users and items in knowledge graphs. However, they ignore the users' personal clicked history sequences that can better reflect users' preferences within a period of time for recommendation. In this paper, we propose a knowledge-aware attentional reasoning network KARN that incorporates the users' clicked history sequences and path connectivity between users and items for recommendation. The proposed KARN not only develops an attention-based RNN to capture the user's history interests from the user's clicked history sequences, but also a hierarchical attentional neural network to reason on paths between users and items for inferring the potential user intents on items. Based on both user's history interest and potential intent, KARN can predict the clicking probability of the user with respective to a candidate item. We conduct experiment on Amazon review dataset, and the experimental results demonstrate the superiority and effectiveness of our proposed KARN model.

Graph neural networks (GNNs) have been successfully used to analyze non-Euclidean network data. Recently, there emerge a number of works to investigate the robustness of GNNs by adding adversarial noises into the graph topology, where gradient-based attacks are widely studied due to their inherent efficiency and high effectiveness. However, the gradient-based attacks often lead to sub-optimal results due to the discrete structure of graph data. To this end, we design a novel exploratory adversarial attack (termed as EpoAtk) to boost the gradient-based perturbations on graphs. The exploratory strategy in EpoAtk includes three phases, generation, evaluation and recombination, with the goal of sidesteping the possible misinformation that the maximal gradient provides. In experiments, EpoAtk is evaluated on benchmark datasets for the task of semi-supervised node classification in different attack settings. Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art attacks with the same attack budgets.

Network representation aims to learn low-dimensional vector representations of network nodes while preserving the inherent properties of the network. For all its popularity, majority of the existing methods focus on exploitation of diverse information, including network topology and semantic information on nodes of network, and ignore their implicit semantics. For example, we all know the saying that birds of a feather flock together. More concretely, semantic information of one node can be influenced by its neighbors' semantic information. Furthermore, even two nodes are not directly connected, they may have similar implicit semantic information (i.e., high-order semantic proximity). Thus, they should be close in the represented vector space. To this end, we propose a Deep Semantic Network Representation approach (DSNR) in the self-translation framework from sequence to sequence. To excavate the implicit semantic information of nodes and capture the high-order semantic proximity, three key components make our approach effective, i.e., aggregation of nodes neighbors' semantic information and enhancement to the semantic feature representations of nodes by a deep autoencoder, integration of nodes semantic information in node identity sequence to generate node semantic sequence, and translation from node semantic sequence to node identity sequence to capture the high-order semantic proximity in an attention-enhanced seq2seq framework. Extensive experiments based on three real-world datasets have verified the effectiveness of our proposed approach11Code is available at https://github.com/DASE4/DSNR.

Trust relationship prediction among people provides valuable supports for decision making, information dissemination, and product promotion in online social networks. Network embedding has achieved promising performance for link prediction by learning node representations that encode intrinsic network structures. However, most of the existing network embedding solutions cannot effectively capture the properties of a trust network that has directed edges and nodes with in/out links. Furthermore, there usually exist rich user attributes in trust networks, such as ratings, reviews, and the rated/reviewed items, which may exert significant impacts on the formation of trust relationships. It is still lacking a network embedding-based method that can adequately integrate these properties for trust prediction. In this work, we develop an AtNE-Trust model to address these issues. We firstly capture user embedding from both the trust network structures and user attributes. Then we design a deep multi-view representation learning module to further mine and fuse the obtained user embedding. Finally, a trust evaluation module is developed to predict the trust relationships between users. Representation learning and trust evaluation are optimized together to capture high-quality user embedding and make accurate predictions simultaneously. A set of experiments against the real-world datasets demonstrates the effectiveness of the proposed approach.

General tasks on crowdsourcing platforms attract more and more workers with different skills and experiences. Existing approaches only leverage the information from tasks with feedback to evaluate worker ability. However, there are millions of tasks without feedback on the platforms. The participating behavior of workers involved in these tasks has not been exploited. In this work, we propose a worker ability model PB-Worker to support general tasks on crowdsourcing platforms. We model the worker latent relation and task latent relation by exploiting the worker participating behavior. To the best of our knowledge, this is the first work to consider the worker participating behavior. Our model is a semi-supervised model that can cover tasks with feedback and tasks without feedback. We employ the ladder network to generate the representations of workers and employ the neural network to predict the worker ability scores. A set of experiments against the real-world dataset from the Zhubajie platform has been conducted. Experimental results show that the output quality of the proposed approach is better than the existing baseline methods.

As communities represent similar opinions, similar functions, similar purposes, etc., community detection is an important and extremely useful tool in both scientific inquiry and data analytics. However, the classic methods of community detection, such as spectral clustering and statistical inference, are falling by the wayside as deep learning techniques demonstrate an increasing capacity to handle high-dimensional graph data with impressive performance. Thus, a survey of current progress in community detection through deep learning is timely. Structured into three broad research streams in this domain – deep neural networks, deep graph embedding, and graph neural networks, this article summarizes the contributions of the various frameworks, models, and algorithms in each stream along with the current challenges that remain unsolved and the future research opportunities yet to be explored.

Social media sites are now becoming very important platforms for product promotion or marketing campaigns. Therefore, there is broad interest in determining ways to guide a site to react more positively to a product with a limited budget. However, the practical significance of the existing studies on this subject is limited for two reasons. First, most studies have investigated the issue in oversimplified networks in which several important network characteristics are ignored. Second, the opinions of individuals are modeled as bipartite states (e.g., support or not) in numerous studies, however, this setting is too strict for many real scenarios. In this study, we focus on social trust networks (STNs), which have the significant characteristics ignored in the previous studies. We generalized a famed continuous-valued opinion dynamics model for STNs, which is more consistent with real scenarios. We subsequently formalized two novel problems for solving the issue in STNs. In addition, we developed two matrix-based methods for these two problems and experiments on realworld datasets to demonstrate the practical utility of our methods.

With the rapid development of mobile Internet technology and the widespread use of mobile devices, it becomes much easier for people to express their opinions on social media. The openness and convenience of social media platforms provide a free expression for people but also cause new social problems. The widespread of false rumors on social media can bring about the panic of the public and damage personal reputation, which makes rumor automatic detection technology become particularly necessary. The majority of existing methods for rumor detection focus on mining effective features from text contents, user profiles, and patterns of propagation. Nevertheless, these methods do not take full advantage of global semantic relations of the text contents, which characterize the semantic commonality of rumors as a key factor for detecting rumors. In this paper, we construct a tweet-word-user heterogeneous graph based on the text contents and the source tweet propagations of rumors. A meta-path based heterogeneous graph attention network framework is proposed to capture the global semantic relations of text contents, together with the global structure information of source tweet propagations for rumor detection. Experiments on real-world Twitter data demonstrate the superiority of the proposed approach, which also has a comparable ability to detect rumors at a very early stage.

RISC-V is an open-source instruction set and now has been examined as a universal standard to unify the heterogeneous platforms. However, current research focuses primarily on the design and fabrication of general-purpose processors based on RISC-V, despite the fact that in the era of IoT (Internet of Things), the fusion of heterogeneous platforms should also take application-specific processors into account. Accordingly, this paper proposes a collaborative RISC-V multi-core system for Deep Neural Network (DNN) accelerators. To the best of our knowledge, this is the first time that a multi-core scheduling architecture for DNN acceleration is formulated and RISC-V is explored as the ISA of a multi-core system to bridge the gap between the memory and the DNN Processor in order to increase the entire system throughput. The experiment realizes a four-stage design of the RISC-V core, and further reveals that a multi-core design along with an appropriate scheduling algorithm can efficiently decrease the runtime and elevate the throughput. Moreover, the experiment also provides us with a constructive suggestion regarding the ideal proportion of the cores to Process Engines (PE), which provides us with significant assistance in building highly efficient AI System-on-Chips (SoCs) in resource-aware situations.

With the rising demand of smart mobility, ride-hailing service is getting popular in the urban regions. These services maintain a system for serving the incoming trip requests by dispatching available vehicles to the pickup points. As the process should be socially and economically profitable, the task of vehicle dispatching is highly challenging, specially due to the time-varying travel demands and traffic conditions. Due to the uneven distribution of travel demands, many idle vehicles could be generated during the operation in different subareas. Most of the existing works on vehicle dispatching system, designed static relocation centers to relocate idle vehicles. However, as traffic conditions and demand distribution dynamically change over time, the static solution can not fit the evolving situations. In this paper, we propose a dynamic future demand aware vehicle dispatching system. It can dynamically search the relocation centers considering both travel demand and traffic conditions. We evaluate the system on real-world dataset, and compare with the existing state-of-the-art methods in our experiments in terms of several standard evaluation metrics and operation time. Through our experiments, we demonstrate that the proposed system significantly improves the serving ratio and with a very small increase in operation cost.

Graph Neural Networks (GNNs) have achieved remarkable performance in the task of the semi-supervised node classification. However, most existing models learn a deterministic classification function, which lack sufficient flexibility to explore better choices in the presence of kinds of imperfect observed data such as the scarce labeled nodes and noisy graph structure. To improve the rigidness and inflexibility of deterministic classification functions, this paper proposes a novel framework named Graph Stochastic Neural Networks (GSNN), which aims to model the uncertainty of the classification function by simultaneously learning a family of functions, i.e., a stochastic function. Specifically, we introduce a learnable graph neural network coupled with a high-dimensional latent variable to model the distribution of the classification function, and further adopt the amortised variational inference to approximate the intractable joint posterior for missing labels and the latent variable. By maximizing the lower-bound of the likelihood for observed node labels, the instantiated models can be trained in an end-to-end manner effectively. Extensive experiments on three real-world datasets show that GSNN achieves substantial performance gain in different scenarios compared with stat-of-the-art baselines.

While numerous approaches have been developed to embed graphs into either Euclidean or hyperbolic spaces, they do not fully utilize the information available in graphs, or lack the flexibility to model intrinsic complex graph geometry. To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph. GIL captures a more informative internal structural features with low dimensions while maintaining conformal invariance of each space. Furthermore, our method endows each node the freedom to determine the importance of each geometry space via a flexible dual feature interaction learning and probability assembling mechanism. Promising experimental results are presented for five benchmark datasets on node classification and link prediction tasks.

Edge computing has enabled extensive reasoning capabilities at the edge of the network. Edge nodes have direct access to edge sources (e.g., sensors, devices) to read and process relevant data, while each sensor/device manufacturer uses their bespoke protocols in the Internet of Things (IoT) environment, hence, addressing compatibility problems to ensure seamless access has become a cumbersome task. A conventional solution is to save all sensor/device protocols in an edge node, however, which brings higher redundancy and hardware expenditure. Hence, we propose a dynamic edge access system (DEA) built on a collaborative IoT architecture. It solves the compatibility issues with low redundancy by customizing access programs. Besides, embedded programmable logic controllers are designed as edge nodes and have been applied in around 78 000 base stations. After implementing DEA, the analysis illustrates that the average improvement of every station's protocol utilization is 96.3% and 66.6%, while the memory footprint is decreased to 4.5% and 33.3% compared with the conventional solution and global dynamic reconfiguration method.

This article explores valid brain electroencephalography (EEG) selection for EEG classification with different classifiers, which has been rarely addressed in previous studies and is mostly ignored by existing EEG processing methods and applications. Importantly, traditional selection methods are not able to select valid EEG signals for different classifiers. This article focuses on a source control-based valid EEG selection to reduce the impact of invalid EEG signals and aims to improve EEG-based classification performance for different classifiers. We propose a novel centroid-based EEG selection approach named CenEEGs, which uses a scale-and-shift-invariance similarity metric to measure similarities of EEG signals and then applies a globally optimal centroid strategy to select valid EEG signals with respect to a similarity threshold. A detailed comparison with several state-of-the-art time series selection methods by using standard criteria on 8 EEG datasets demonstrates the efficacy and superiority of CenEEGs for different classifiers.

In image analysis, image samples are always represented by multiple view features and associated with multiple class labels for better interpretation. However, multiple view data may include noisy, irrelevant and redundant features, while multiple class labels can be noisy and incomplete. Due to the special data characteristic, it is hard to perform feature selection on multi-view multi-label data. To address these challenges, in this paper, we propose a novel multi-view multi-label sparse feature selection (MSFS) method, which exploits both view relations and label correlations to select discriminative features for further learning. Specifically, the multi-labeled information is decomposed into a reduced latent label representation to capture higher level concepts and correlations among multiple labels. Multiple local geometric structures are constructed to exploit visual similarities and relations for different views. By taking full advantage of the latent label representation and multiple local geometric structures, the sparse regression model with an l2,1-norm and an Frobenius norm (F-norm) penalty terms is utilized to perform hierarchical feature selection, where the F-norm penalty performs high-level (i.e., view-wise) feature selection to preserve the informative views and the l2,1-norm penalty conducts low-level (i.e., row-wise) feature selection to remove noisy features. To solve the proposed formulation, we also devise a simple yet efficient iterative algorithm. Experiments and comparisons on real-world image datasets demonstrate the effectiveness and potential of MSFS.

The latent friend recommendation in online social media is interesting, yet challenging, because the user-item ratings and the user-user relationships are both sparse. In this paper, we propose a new dual implicit mining-based latent friend recommendation model that simultaneously considers the implicit interest topics of users and the implicit link relationships between the users in the local topic cliques. Specifically, we first propose an algorithm called all reviews from a user and all tags from their corresponding items to learn the implicit interest topics of the users and their corresponding topic weights, then compute the user interest topic similarity using a symmetric Jensen-Shannon divergence. After that, we adopt the proposed weighted local random walk with restart algorithm to analyze the implicit link relationships between the users in the local topic cliques and calculate the weighted link relationship similarity between the users. Combining the user interest topic similarity with the weighted link relationship similarity in a unified way, we get the final latent friend recommendation list. The experiments on real-world datasets demonstrate that the proposed method outperforms the state-of-the-art latent friend recommendation methods under four different types of evaluation metrics.

Graphs are commonly used to represent objects, such as images and text, for pattern classification. In a dynamic world, an object may continuously evolve over time, and so does the graph extracted from the underlying object. These changes in graph structure with respect to the temporal order present a new representation of the graph, in which an object corresponds to a set of time-variant graphs. In this paper, we formulate a novel time-variant graph classification task and propose a new graph feature, called a graph-shapelet pattern, for learning and classifying time-variant graphs. Graph-shapelet patterns are compact and discriminative graph transformation subsequences. A graph-shapelet pattern can be regarded as a graphical extension of a shapelet-a class of discriminative features designed for vector-based temporal data classification. To discover graph-shapelet patterns, we propose to convert a time-variant graph sequence into time-series data and use the discovered shapelets to find graph transformation subsequences as graph-shapelet patterns. By converting each graph-shapelet pattern into a unique tokenized graph transformation sequence, we can measure the similarity between two graph-shapelet patterns and therefore classify time-variant graphs. Experiments on both synthetic and real-world data demonstrate the superior performance of the proposed algorithms.

Automatic knowledge graph construction seeks to build a knowledge graph from unstructured text in a specific domain or cross multiple domains, without human intervention. IEEE ICDM 2019 and ICBK 2019 invited teams from both degree-granting institutions and industrial labs to compete in the 2019 Knowledge Graph Contest by automatically constructing knowledge graphs in at least two different domains. This article reports the outcomes of the Contest. The participants were expected to build a model to extract knowledge represented as triplets from text data and develop a web application to visualize the triplets. Awards were given to five teams. Their models and key techniques used to construct knowledge graphs are summarized.

Cross-lingual Entity Alignment (CEA) aims at identifying entities with their counterparts in different language knowledge graphs. Knowledge embedding alignment plays an important role in CEA due to its advantages of easy implementation and run-time robustness. However, existing embedding alignment methods haven't considered the problem of embedding distribution alignment which refers to the alignment of spatial shapes of embedding spaces. To this end, we present a new Adversarial Knowledge Embedding framework (AKE for short) that jointly learns the representation, mapping and adversarial modules in an end-to-end manner. By reducing the discrepancy of embedding distributions, AKE can approximately preserve an isomorphism between source and target embeddings. In addition, we introduce two new orthogonality constraints into mapping to obtain the self-consistency and numerical stability of transformation. Experiments on real-world datasets demonstrate that our method significantly outperforms state-of-the-art baselines.

Trust prediction in online social networks is crucial for information dissemination, product promotion, and decision making. Existing work on trust prediction mainly utilizes the network structure or the low-rank approximation of a trust network. These approaches can suffer from the problem of data sparsity and prediction accuracy. Inspired by the homophily theory, which shows a pervasive feature of social and economic networks that trust relations tend to be developed among similar people, we propose a novel deep user model for trust prediction based on user similarity measurement. It is a comprehensive data sparsity insensitive model that combines a user review behavior and the item characteristics that this user is interested in. With this user model, we firstly generate a user's latent features mined from user review behavior and the item properties that the user cares. Then we develop a pair-wise deep neural network to further learn and represent these user features. Finally, we measure the trust relations between a pair of people by calculating the user feature vector cosine similarity. Extensive experiments are conducted on two real-world datasets, which demonstrate the superior performance of the proposed approach over the representative baseline works.

Developing effective network embedding methods for social trust networks (STNs) is a non-trivial problem because two key pieces of information need to be preserved simultaneously: a user's relations to latent factors and the trust transfer patterns that govern what type of relationship will form. In this study, we propose a novel social trust network embedding method (STNE) to address these issues. Specifically, we present a modified Skip-Gram model with negative sampling to jointly learn latent factor features, along with the trust transfer pattern features. Moreover, we define a flexible notion about a user's latent relationships with other users, which generates reliable negative samples for optimization. Extensive experiments on several real-world networks demonstrate the efficacy of the proposed STNE.

Predicting pairs of anchor users plays an important role in the cross-network analysis. Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction. To this end, we present a deep active learning model for anchor user prediction (DALAUP for short). However, active learning for anchor user sampling meets the challenges of non-i.i.d. user pair data caused by network structures and the correlation among anchor or non-anchor user pairs. To solve the challenges, DALAUP uses a couple of neural networks with shared-parameter to obtain the vector representations of user pairs, and ensembles three query strategies to select the most informative user pairs for labeling and model training. Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches.

Trust evaluation of people and information on Twitter is critical for maintaining a healthy online social environment. How to evaluate the trustworthiness of users and tweets becomes a challenging question. In this demo, we show how our proposed CoTrRank approach deal with this problem. This approach models users and tweets in two coupled networks and calculate their trust values in different trust spaces. In particular, our solution provides a configurable way when mapping the calculated raw evidences to the trust values. The CoTrRank demo system has an interactive interface to show how our proposed approach produces more effective and adaptive trust evaluation results comparing with baseline methods.

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the structure and inherent properties of the network. Most existing network embedding methods didn't consider network noise. However, it is almost impossible to observe the actual structure of a real-world network without noise. The noise in the network will affect the performance of network embedding dramatically. In this paper, we aim to exploit node similarity to address the problem of social network embedding with noise and propose a node similarity preserving (NSP) embedding method. NSP exploits a comprehensive similarity index to quantify the authenticity of the observed network structure. Then we propose an algorithm to construct a correction matrix to reduce the influence of noise. Finally, an objective function for accurate network embedding is proposed and an efficient algorithm to solve the optimization problem is provided. Extensive experimental results on a variety of applications of real-world networks with noise show the superior performance of the proposed method over the state-of-the-art methods.

Multilingual knowledge graphs constructed by entity alignment are the indispensable resources for numerous AI-related applications. Most existing entity alignment methods only use the triplet-based knowledge to find the aligned entities across multilingual knowledge graphs, they usually ignore the neighborhood subgraph knowledge of entities that implies more richer alignment information for aligning entities. In this paper, we incorporate neighborhood subgraph-level information of entities, and propose a neighborhood-aware attentional representation method NAEA for multilingual knowledge graphs. NAEA devises an attention mechanism to learn neighbor-level representation by aggregating neighbors' representations with a weighted combination. The attention mechanism enables entities not only capture different impacts of their neighbors on themselves, but also attend over their neighbors' feature representations with different importance. We evaluate our model on two real-world datasets DBP15K and DWY100K, and the experimental results show that the proposed model NAEA significantly and consistently outperforms state-of-the-art entity alignment models.

With the development of social media and the popularity of mobile devices, it becomes increasingly easy to post rumors and spread rumors on social media. Widespread rumors may cause public panic and negative impact on individuals, which makes the automatic detection of rumors become necessary. Most existing methods for automatic rumor detection focus on modeling features related to contents, users and propagation patterns based on feature engineering, but few work consider the existence of graph structural information in the user behavior. In this paper, we propose a model that leverages graph convolutional networks to capture user behavior effectively for rumor detection. Our model is composed of three modules: 1) a user encoder that models users attributes and behaviors based on graph convolutional networks to obtain user representation; 2) a propagation tree encoder, which encodes the structure of the rumor propagation tree as a vector with bridging the content semantics and propagation clues; 3) an integrator that integrates the output of the above modules to identify rumors. Experimental results on two public Twitter datasets show that our model achieves much better performance than the state-of-the-art methods.

Evolutionary clustering is a way of detecting the evolving patterns of communities in dynamic social networks. In principle, the detection process seeks to simultaneously maximize clustering accuracy at the current time step and minimize the clustering drift between two successive time steps. Several evolutionary clustering methods have been developed in an attempt to find the best trade-off between clustering accuracy and temporal smoothness, but the classic genetic operators in these methods do not make the best of the inter- and intra-connected relationships between nodes, which limits their effectiveness. To overcome this problem, we propose a novel migration operator to work in tandem with classic genetic operators to improve the discovery of evolving community structures. The operator is implemented within an existing genetic algorithm which relies on a genome representation under a decomposition framework that formulates evolutionary community detection as a multiobjective optimization problem. Moreover, we present a new method of calculating modularity directly from a genome matrix as the objective for measuring the snapshot quality, which results in a wider search space for finding the optimal solution. Experimental results over several synthetic networks and one real-world dynamic social network suggest that our method is superior to two other state-of-the-art methods in terms of both accuracy and smoothness in discovering evolving community structures in dynamic social networks.

Network embedding is an efficient method to learn low-dimensional representations of vertexes in networks since the network structure can be captured and preserved through this process. Unlike shallow models, deep neural network framework is able to capture the highly non-linear network structure. Therefore, it can achieve much better performance in comparison of traditional network embedding methods. However, few attention has been paid to the smoothness of such models, in contrast to numerous research works for image and text fields. Methods without smoothness are not robust enough, which means that slight changes on network may lead dramatic changes on the embedding results. Hence, how to find a smooth deep framework is still an open yet important problem. To this end, in this paper, we propose a Smooth Deep Network Embedding method, namely SmNE, which generates stable and reliable embedding results. Empirically, we conduct experiments on real-world networks. The results show that compared to the state-of-the-art methods, our proposed method can achieve significant gains in several applications.

Link prediction in signed social networks is an important and challenging problem in social network analysis. To produce the most accurate prediction results, two questions must be answered: (1) Which unconnected node pairs are likely to be connected by a link in future? (2) What will the signs of the new links be? These questions are challenging, and current research seldom well solves both issues simultaneously. Additionally, neutral social relationships, which are common in many social networks can affect the accuracy of link prediction. Yet neutral links are not considered in most existing methods. Hence, in this paper, we propose a s igned l atent f actor (SLF) model that answers both these questions and, additionally, considers four types of relationships: positive, negative, neutral and no relationship at all. The model links social relationships of different types to the comprehensive, but opposite, effects of positive and negative SLFs. The SLF vectors for each node are learned by minimizing a negative log-likelihood objective function. Experiments on four real-world signed social networks support the efficacy of the proposed model.

Time series has been a popular research topic over the past decade. Salient subsequences of time series that can benefit the learning task, e.g., classification or clustering, are called shapelets. Shapelet-based time series learning extracts these types of salient subsequences with highly informative features from a time series. Most existing methods for shapelet discovery must scan a large pool of candidate subsequences, which is a time-consuming process. A recent work, [1] , uses regression learning to discover shapelets in a time series; however, it only considers learning shapelets from labeled time series data. This paper proposes an Unsupervised Salient Subsequence Learning (USSL) model that discovers shapelets without the effort of labeling. We developed this new learning function by integrating the strengths of shapelet learning, shapelet regularization, spectral analysis and pseudo-label to simultaneously and automatically learn shapelets to help clustering unlabeled time series better. The optimization model is iteratively solved via a coordinate descent algorithm. Experiments show that our USSL can learn meaningful shapelets, with promising results on real-world and synthetic data that surpass current state-of-the-art unsupervised time series learning methods.

This paper formulates the problem of learning discriminative features (i.e., segments) from networked time-series data, considering the linked information among time series. For example, social network users are considered to be social sensors that continuously generate social signals represented as a time series. The discriminative segments are often referred to as shapelets in a time series. Extracting shapelets for time-series analysis has been widely studied. However, existing works on shapelet selection assume that the time series are independent and identically distributed. This assumption restricts their applications to social networked time-series analysis since a user's actions can be correlated to his/her social affiliations. In this paper, we propose a novel network regularized least squares (NetRLS) feature selection model that combines typical time-series data and user network data for analysis. Experiments on real-world Twitter, Weibo, and DBLP networked time-series data demonstrate the performance of the proposed method. NetRLS performs better than the representative baselines on four evaluation criteria, namely classification accuracy, area under the curve (AUC), F1-score, and statistical significance analysis. NetRLS also has competitive running time as the baselines.

Unlabeled, multi-view data presents a considerable challenge in many real-world data analysis tasks. These data are worth exploring because they often contain complementary information that improves the quality of the analysis results. Clustering with multi-view data is a particularly challenging problem as revealing the complex data structures between many feature spaces demands discriminative features that are specific to the task and, when too few of these features are present, performance suffers. Extreme learning machines (ELMs) are an emerging form of learning model that have shown an outstanding representation ability and superior performance in a range of different learning tasks. Motivated by the promise of this advancement, we have developed a novel multi-view fusion clustering framework based on an ELM, called MVEC. MVEC learns the embeddings from each view of the data via the ELM network, then constructs a single unified embedding according to the correlations and dependencies between each embedding and automatically weighting the contribution of each. This process exposes the underlying clustering structures embedded within multi-view data with a high degree of accuracy. A simple yet efficient solution is also provided to solve the optimization problem within MVEC. Experiments and comparisons on eight different benchmarks from different domains confirm MVEC’s clustering accuracy.

Based on the performance of entire social networks, anomaly analysis for evolving social networks generally ignores the otherness of the evolutionary behaviors of different nodes, such that it is difficult to precisely identify the anomalous evolutionary behaviors of nodes ( AEBN ). Assuming that a node's evolutionary behavior that generates and removes edges normally follows stable evolutionary mechanisms, this study focuses on detecting and assessing AEBN, whose evolutionary mechanisms deviate from their past mechanisms, and proposes a link prediction detection ( LPD ) method and a matrix perturbation assessment ( MPA ) method. LPD describes a node's evolutionary behavior by fitting its evolutionary mechanism, and designs indexes for edge generation and removal to evaluate the extent to which the evolutionary mechanism of a node's evolutionary behavior can be fitted by a link prediction algorithm. Furthermore, it detects AEBN by quantifying the differences among behavior vectors that characterize the node's evolutionary behaviors in different periods. In addition, MPA considers AEBN as a perturbation of the social network structure, and quantifies the effect of AEBN on the social network structure based on matrix perturbation analysis. Extensive experiments on eight disparate real-world networks demonstrate that analyzing AEBN from the perspective of evolutionary mechanisms is important and beneficial.

Due to its simplicity, efficiency, and efficacy, naive Bayes (NB) has continued to be one of the top 10 algorithms in the data mining and machine learning community. Of numerous approaches to alleviating its conditional independence assumption, feature weighting has placed more emphasis on highly predictive features than those that are less predictive. In this paper, we argue that for NB highly predictive features should be highly correlated with the class (maximum mutual relevance), yet uncorrelated with other features (minimum mutual redundancy). Based on this premise, we propose a correlation-based feature weighting (CFW) filter for NB. In CFW, the weight for a feature is a sigmoid transformation of the difference between the feature-class correlation (mutual relevance) and the average feature-feature intercorrelation (average mutual redundancy). Experimental results show that NB with CFW significantly outperforms NB and all the other existing state-of-the-art feature weighting filters used to compare. Compared to feature weighting wrappers for improving NB, the main advantages of CFW are its low computational complexity (no search involved) and the fact that it maintains the simplicity of the final model. Besides, we apply CFW to text classification and have achieved remarkable improvements.

This paper solves the problem of nonrigid point set registration by designing a robust transformation learning scheme. The principle is to iteratively establish point correspondences and learn the nonrigid transformation between two given sets of points. In particular, the local feature descriptors are used to search the correspondences and some unknown outliers will be inevitably introduced. To precisely learn the underlying transformation from noisy correspondences, we cast the point set registration into a semisupervised learning problem, where a set of indicator variables is adopted to help distinguish outliers in a mixture model. To exploit the intrinsic structure of a point set, we constrain the transformation with manifold regularization which plays a role of prior knowledge. Moreover, the transformation is modeled in the reproducing kernel Hilbert space, and a sparsity-induced approximation is utilized to boost efficiency. We apply the proposed method to learning motion flows between image pairs of similar scenes for visual homing, which is a specific type of mobile robot navigation. Extensive experiments on several publicly available data sets reveal the superiority of the proposed method over state-of-the-art competitors, particularly in the context of the degenerated data.

Social recommendation, which aims to exploit social information to improve the quality of a recommender system, has attracted an increasing amount of attention in recent years. A large portion of existing social recommendation models are based on the tractable assumption that users consider the same factors to make decisions in both recommender systems and social networks. However, this assumption is not in concert with real-world situations, since users usually show different preferences in different scenarios. In this paper, we investigate how to exploit the differences between user preference in recommender systems and that in social networks, with the aim to further improve the social recommendation. In particular, we assume that the user preferences in different scenarios are results of different linear combinations from a more underlying user preference space. Based on this assumption, we propose a novel social recommendation framework, called social recommendation with an essential preferences space (SREPS), which simultaneously models the structural information in the social network, the rating and the consumption information in the recommender system under the capture of essential preference space. Experimental results on four real-world datasets demonstrate the superiority of the proposed SREPS model compared with seven state-of-the-art social recommendation methods.

In this paper, we propose a novel image inpainting framework consisting of an interpolation step and a low-rank tensor completion step. More specifically, we first initial the image with triangulation-based linear interpolation, and then we find similar patches for each missing-entry centered patch. Treating a group of patch matrices as a tensor, we employ the recently proposed effective t-SVD tensor completion algorithm with a warm start strategy to inpaint it. We observe that the interpolation step is such a rough initialization that the similar patch we found may not exactly match with the reference, so we name the problem as Patch Mismatch and analyse the error caused by it thoroughly. Our theoretical analysis shows that the error caused by Patch Mismatch can be decomposed into two components, one of which can be bounded by a reasonable assumption named local patch similarity, and another part is lower than that using matrix. Experiments on real images verify our method's superiority to the state-of-the-art inpainting methods.

Fraud detection is of great importance because fraudulent behaviors may mislead consumers or bring huge losses to enterprises. Due to the lockstep feature of fraudulent behaviors, fraud detection problem can be viewed as finding suspicious dense blocks in the attributed bipartite graph. In reality, existing attribute-based methods are not adversarially robust, because fraudsters can take some camouflage actions to cover their behavior attributes as normal. More importantly, existing structural information based methods only consider shallow topology structure, making their effectiveness sensitive to the density of suspicious blocks. In this paper, we propose a novel deep structure learning model named DeepFD to differentiate normal users and suspicious users. DeepFD can preserve the non-linear graph structure and user behavior information simultaneously. Experimental results on different types of datasets demonstrate that DeepFD outperforms the state-of-the-art baselines.

Tracking a moving target of interests from a space-borne satellite video is really a difficulty, since the target usually occupies only a few pixels in each frame of satellite video. Even it is a long train. Most state-of-the-art tracking algorithms mainly rely on luminance or color features, failing to handle this video tracking problem due to the extremely inadequate quality of targets features. To overcome this difficulty, we propose a velocity correlation filter (VCF), employing velocity feature and inertia mechanism to construct a kernel correlation filter for satellite video targets tracking. The velocity feature has a high discriminative ability to detect moving targets in satellite videos and the inertia mechanism can prevent model drift adaptively. Experimental results on three real satellite video datasets show our proposed approach outperforms state-of-the-art tracking methods with a more than 100 frames per second.

Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains. In this manuscript, we develop a novel method, transfer latent representation (TLR), to learn a better latent space. Specifically, we design an objective function based on a simple linear autoencoder to derive the latent representations of both domains. The encoder in the autoencoder aims to project the data of both domains into a robust latent space. Besides, the decoder imposes an additional constraint to reconstruct the original data, which can preserve the common properties of both domains and reduce the noise that causes domain shift. Experiments on cross-domain tasks demonstrate the advantages of TLR over competing methods.

Unsupervised domain adaptation aims to predict unlabeled target domain data by taking advantaging of labeled source domain data. This problem is hard to solve mainly because of the limitation of target domain label and the difference between both domains. To overcome these two difficulties, many researchers have proposed to assign pseudo labels for the unlabeled target domain data and then project both domain data into a common subspace. The use of pseudo labels, however, lack of theoretical basis and thus may not gain ideal classification results eventually. Therefore, in this work we propose a novel method called Probabilistic Graph Embedding(PGE). PGE first derives probabilities that the target domain instances belong to each category, which is believed to be able to explore target domain better. We then obtain a projection matrix by constructing a within-class probabilistic graph. This projection matrix can embed both domains into a shared subspace where domain shift is largely diminished. Experiments on object recognition cross-domain datasets show that PGE is more effective and robust than the state-of-art unsupervised domain adaptation methods.

Network embedding has been recently used in social network recommendations by embedding low-dimensional representations of network items for recommendation. However, existing item recommendation models in social networks suffer from two limitations. First, these models partially use item information and mostly ignore important contextual information in social networks such as textual content and social tag information. Second, network embedding and item recommendations are learned in two independent steps without any interaction. To this end, we in this paper consider item recommendations based on heterogeneous information sources. Specifically, we combine item structure, textual content and tag information for recommendation. To model the multi-source heterogeneous information, we use two coupled neural networks to capture the deep network representations of items, based on which a new recommendation model Collaborative multi-source Deep Network Embedding (CDNE for short) is proposed to learn different latent representations. Experimental results on two real-world data sets demonstrate that CDNE can use network representation learning to boost the recommendation performance.

Most of current network representation models are learned in unsupervised fashions, which usually lack the capability of discrimination when applied to network analysis tasks, such as node classification. It is worth noting that label information is valuable for learning the discriminative network representations. However, labels of all training nodes are always difficult or expensive to obtain and manually labeling all nodes for training is inapplicable. Different sets of labeled nodes for model learning lead to different network representation results. In this paper, we propose a novel method, termed as ANRMAB, to learn the active discriminative network representations with a multi-armed bandit mechanism in active learning setting. Specifically, based on the networking data and the learned network representations, we design three active learning query strategies. By deriving an effective reward scheme that is closely related to the estimated performance measure of interest, ANRMAB uses a multi-armed bandit mechanism for adaptive decision making to select the most informative nodes for labeling. The updated labeled nodes are then used for further discriminative network representation learning. Experiments are conducted on three public data sets to verify the effectiveness of ANRMAB.

Matrix Factorization based methods, e.g., the Concept Factorization (CF) and Nonnegative Matrix Factorization (NMF), have been proved to be efficient and effective for data clustering tasks. In recent years, various graph extensions of CF and NMF have been proposed to explore intrinsic geometrical structure of data for the purpose of better clustering performance. However, many methods build the affinity matrix used in the manifold structure directly based on the input data. Therefore, the clustering results are highly sensitive to the input data. To further improve the clustering performance, we propose a novel manifold concept factorization model with adaptive neighbor structure to learn a better affinity matrix and clustering indicator matrix at the same time. Technically, the proposed model constructs the affinity matrix by assigning the adaptive and optimal neighbors to each point based on the local distance of the learned new representation of the original data with itself as a dictionary. Our experimental results present superior performance over the state-of-the-art alternatives on numerous datasets.

Cross-Domain Recommendation (CDR) and Cross-System Recommendations (CSR) are two of the promising solutions to address the long-standing data sparsity problem in recommender systems. They leverage the relatively richer information, e.g., ratings, from the source domain or system to improve the recommendation accuracy in the target domain or system. Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy. However, this is a very challenging task because of the complex relationships between the latent factors of the source and target domains or systems. To this end, in this paper, we propose a Deep framework for both Cross-Domain and Cross-System Recommendations, called DCDCSR, based on Matrix Factorization (MF) models and a fully connected Deep Neural Network (DNN). Specifically, DCDCSR first employs the MF models to generate user and item latent factors and then employs the DNN to map the latent factors across domains or systems. More importantly, we take into account the rating sparsity degrees of individual users and items in different domains or systems and use them to guide the DNN training process for utilizing the rating data more effectively. Extensive experiments conducted on three real-world datasets demonstrate that DCDCSR framework outperforms the state-of-the-art CDR and CSR approaches in terms of recommendation accuracy.

Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failure of training due to the vanishing gradient (or exploding gradient) and local optima problems. In this paper, we present SEvoAE method based on using Evolutionary Multiobjective optimization (EMO) algorithm to train single layer auto-encoder, and sequentially learning deeper representation in a stacking way. SEvoAE is able to achieve accurate feature representation with good sparseness by globally simultaneously optimizing two conflicting objective functions and allows users to flexibly design objective functions and evolutionary optimizers. We compare results of the proposed method with existing architectures for seven classification problems, showing that the proposed method is able to outperform existing methods with a reduced risk of overfitting the training data.

Social recommendation incorporates the social information of the user, such as friend relationship and trust relationship into the traditional recommendation system. From this point of view, social recommendation expands the function of the traditional recommendation to some extent. However, the existing social recommendation methods mostly focus on the general social relation between users and neglects the refinement of group information based on individual interest and trust. To this end, this paper proposes a novel social recommendation model based on the collective intelligence awareness driven by individual interest and trust. Experiments on two real-world datasets demonstrate that the proposed social recommendation method based on group information and individual feature outperforms the three baseline methods on the two evaluation metrics MAE and RMSE.

Detecting fraudsters is a meaningful problem for both users and e-commerce platform. Existing graph-based approaches mainly adopt shallow models, which cannot capture the highly non-linear relationship between vertexes in a bipartite graph composed of users and items. To address this issue, in this paper we propose a joint deep structure embedding approach FraudNE for fraud detection that (a) can preserve the highly non-linear structural information of networks, (b) is robust to sparse networks, (c) embeds different types of vertexes jointly in the same latent space. It is worth mentioning that we can detect multiple fraudulent groups without the number of groups as a priori. Compared with baselines, our method achieved significant accuracy improvement.

Automated prostate segmentation in 3D medical images play an important role in many clinical applications, such as diagnosis of prostatitis, prostate cancer and enlarged prostate. However, it is still a challenging task due to the complex background, lacking of clear boundary and various shape and texture between the slices. In this paper, we propose a novel 3D convolutional neural network with densely-connected layers to automatically segment the prostate from Magnetic Resonance(MR) images. Compared with other methods, our method has three compelling advantages. First, our model can effectively detect the prostate region in a volume-to-volume manner by utilizing the 3D convolution rather than the 3D convolution, which can fully exploit both spatial and region information. Second, the proposed network architecture alleviates the vanishing-gradient problem, strengthens the information propagation between layers, overcomes the problem of over-fitting and makes the network deeper by adopting a densely-connected manner. Third, besides the densely-connected manner inside each block, we also adopt the long connections strategy between blocks. We evaluate our proposed model on prostate dataset. The experimental results show that our model achieved significant segmentation results and outperformed other state-of-arts methods.

Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performance and most previously developed methods ignore the necessity of EEG selection for classification. To this end, this paper proposes a novel maximum weight clique-based EEG selection approach, named mwcEEGs, to map EEG selection to searching maximum similarity-weighted cliques from an improved Fréchet distance-weighted undirected EEG graph simultaneously considering edge weights and vertex weights. Our mwcEEGs improves the classification performance by selecting intra-clique pairwise similar and inter-clique discriminative EEGs with similarity threshold δ. Experimental results demonstrate the algorithm effectiveness compared with the state-of-the-art time series selection algorithms on real-world EEG datasets.

Multi-instance learning (MIL) is a useful tool for tackling labeling ambiguity in learning because it allows a bag of instances to share one label. Bag mapping transforms a bag into a single instance in a new space via instance selection and has drawn significant attention recently. To date, most existing work is based on the original space, using all instances inside each bag for bag mapping, and the selected instances are not directly tied to an MIL objective. As a result, it is difficult to guarantee the distinguishing capacity of the selected instances in the new bag mapping space. In this paper, we propose a discriminative mapping approach for multi-instance learning (MILDM) that aims to identify the best instances to directly distinguish bags in the new mapping space. Accordingly, each instance bag can be mapped using the selected instances to a new feature space, and hence any generic learning algorithm, such as an instance-based learning algorithm, can be used to derive learning models for multi-instance classification. Experiments and comparisons on eight different types of real-world learning tasks (including 14 data sets) demonstrate that MILDM outperforms the state-of-the-art bag mapping multi-instance learning approaches. Results also confirm that MILDM achieves balanced performance between runtime efficiency and classification effectiveness.

Random forests (RFs) are recognized as one type of ensemble learning method and are effective for the most classification and regression tasks. Despite their impressive empirical performance, the theory of RFs has yet been fully proved. Several theoretically guaranteed RF variants have been presented, but their poor practical performance has been criticized. In this paper, a novel RF framework is proposed, named Bernoulli RFs (BRFs), with the aim of solving the RF dilemma between theoretical consistency and empirical performance. BRF uses two independent Bernoulli distributions to simplify the tree construction, in contrast to the RFs proposed by Breiman. The two Bernoulli distributions are separately used to control the splitting feature and splitting point selection processes of tree construction. Consequently, theoretical consistency is ensured in BRF, i.e., the convergence of learning performance to optimum will be guaranteed when infinite data are given. Importantly, our proposed BRF is consistent for both classification and regression. The best empirical performance is achieved by BRF when it is compared with state-of-the-art theoretical/consistent RFs. This advance in RF research toward closing the gap between theory and practice is verified by the theoretical and experimental studies in this paper.

Many applications involve objects containing structure and rich content information, each describing different feature aspects of the object. Graph learning and classification is a common tool for handling such objects. To date, existing graph classification has been limited to the single-graph setting with each object being represented as one graph from a single structure-view. This inherently limits its use to the classification of complicated objects containing complex structures and uncertain labels. In this paper, we advance graph classification to handle multigraph learning for complicated objects from multiple structure views, where each object is represented as a bag containing several graphs and the label is only available for each graph bag but not individual graphs inside the bag. To learn such graph classification models, we propose a multistructure-view bag constrained learning (MSVBL) algorithm, which aims to explore substructure features across multiple structure views for learning. By enabling joint regularization across multiple structure views and enforcing labeling constraints at the bag and graph levels, MSVBL is able to discover the most effective substructure features across all structure views. Experiments and comparisons on real-world data sets validate and demonstrate the superior performance of MSVBL in representing complicated objects as multigraph for classification, e.g., MSVBL outperforms the state-of-the-art multiview graph classification and multiview multi-instance learning approaches.

In many time-aware item recommender systems, modeling the accurate evolution of both user profiles and the contents of items over time is essential. However, most existing methods focus on learning users' dynamic interests, where the contents of items are assumed to be stable over time. They thus fail to capture the dynamic changes in the item's contents. In this paper, we present a novel method CDUE for time-aware item recommendation, which captures the evolution of both user's interests and item's contents information via topic dynamics. Specifically, we propose a dynamic sparse topic model to track the evolution of topics for changes in items' contents over time and adapt a vector autoregressive model to profile users' dynamic interests. The item's topics and user's interests and their evolutions are learned collaboratively and simultaneously into a unified learning framework. Experimental results on two real-world data sets demonstrate the quality and effectiveness of the proposed method and show that our method can be used to make better future recommendations.

Due to the rapid growth of event-based social networks (EBSNs), event recommendation which helps users find their preferred events has become a popular topic. Different from movies or books in conventional recommendation problem, events usually have recommendation lifetimes and almost all the events to be recommended are upcoming, which brings a severe cold start problem. To achieve better event recommendation performance, we formulates multiple interactions among users, events, groups and locations into an unified framework and propose a collective pairwise matrix factorization (CPMF) model to estimate users' pairwise preferences on events, groups and locations. We further develop an efficient stochastic gradient descent algorithm for the model learning. We conduct experiments on real-world Meetup datasets and the experimental results demonstrate that our CPMF model can outperform the state-of-the-art methods.

How to maintain relative high diversity is important to avoid premature convergence in population-based optimization methods. Island model is widely considered as a major approach to achieve this because of its flexibility and high efficiency. The model maintains a group of sub-populations on different islands and allows sub-populations to interact with each other via predefined migration policies. However, current island model has some drawbacks. One is that after a certain number of generations, different islands may retain quite similar, converged sub-populations thereby losing diversity and decreasing efficiency. Another drawback is that determining the number of islands to maintain is also very challenging. Meanwhile initializing many sub-populations increases the randomness of island model. To address these issues, we proposed a dynamic island model (DIM-SP) which can force each island to maintain different sub-populations, control the number of islands dynamically and starts with one sub-population. The proposed island model outperforms the other three state-of-the-art island models in three baseline optimization problems including job shop scheduler, travelling salesmen, and quadratic multiple knapsack.

In this paper we study a new problem of online discovering diffusion provenances in large networks. Existing work on network diffusion provenance identification focuses on offline learning where data collected from network detectors are static and a snapshot of the network is available before learning. However, an offline learning model does not meet the need for early warning, real-time awareness, or a real-time response to malicious information spreading in networks. To this end, we propose an online regression model for real-time diffusion provenance identification. Specifically, we first use offline collected network cascades to infer the edge transmission weights, and then use an online l 1 non-convex regression model as the identification model. The proposed methods are empirically evaluated on both synthetic and real-world networks. Experimental results demonstrate the effectiveness of the proposed model.

Deep networks have achieved excellent performance in learning representation from visual data. However, the supervised deep models like convolutional neural network require large quantities of labeled data, which are very expensive to obtain. To solve this problem, this paper proposes an unsupervised deep network, called the stacked convolutional denoising auto-encoders, which can map images to hierarchical representations without any label information. The network, optimized by layer-wise training, is constructed by stacking layers of denoising auto-encoders in a convolutional way. In each layer, high dimensional feature maps are generated by convolving features of the lower layer with kernels learned by a denoising auto-encoder. The auto-encoder is trained on patches extracted from feature maps in the lower layer to learn robust feature detectors. To better train the large network, a layer-wise whitening technique is introduced into the model. Before each convolutional layer, a whitening layer is embedded to sphere the input data. By layers of mapping, raw images are transformed into high-level feature representations which would boost the performance of the subsequent support vector machine classifier. The proposed algorithm is evaluated by extensive experimentations and demonstrates superior classification performance to state-of-the-art unsupervised networks.

Multitask learning (MTL) is commonly used for jointly optimizing multiple learning tasks. To date, all existing MTL methods have been designed for tasks with feature-vector represented instances, but cannot be applied to structure data, such as graphs. More importantly, when carrying out MTL, existing methods mainly focus on exploring overall commonality or disparity between tasks for learning, but cannot explicitly capture task relationships in the feature space, so they are unable to answer important questions, such as what exactly is shared between tasks and what is the uniqueness of one task differing from others? In this paper, we formulate a new multitask graph learning problem, and propose a task sensitive feature exploration and learning algorithm for multitask graph classification. Because graphs do not have features available, we advocate a task sensitive feature exploration and learning paradigm to jointly discover discriminative subgraph features across different tasks. In addition, a feature learning process is carried out to categorize each subgraph feature into one of three categories: (1) common feature; (2) task auxiliary feature; and (3) task specific feature, indicating whether the feature is shared by all tasks, by a subset of tasks, or by only one specific task, respectively. The feature learning and the multiple task learning are iteratively optimized to form a multitask graph classification model with a global optimization goal. Experiments on real-world functional brain analysis and chemical compound categorization demonstrate the algorithm's performance. Results confirm that our method can be used to explicitly capture task correlations and uniqueness in the feature space, and explicitly answer what are shared between tasks and what is the uniqueness of a specific task.

In this paper, we advance graph classification to handle multi-graph learning for complicated objects, where each object is represented as a bag of graphs and the label is only available to each bag but not individual graphs. In addition, when training classifiers, users are only given a handful of positive bags and many unlabeled bags, and the learning objective is to train models to classify previously unseen graph bags with maximum accuracy. To achieve the goal, we propose a positive and unlabeled multi-graph learning (puMGL) framework to first select informative subgraphs to convert graphs into a feature space. To utilize unlabeled bags for learning, puMGL assigns a confidence weight to each bag and dynamically adjusts its weight value to select "reliable negative bags." A number of representative graphs, selected from positive bags and identified reliable negative graph bags, form a "margin graph pool" which serves as the base for deriving subgraph patterns, training graph classifiers, and further updating the bag weight values. A closed-loop iterative process helps discover optimal subgraphs from positive and unlabeled graph bags for learning. Experimental comparisons demonstrate the performance of puMGL for classifying real-world complicated objects.

Graphs are popularly used to represent objects with shared dependency relationships. To date, all existing graph clustering algorithms consider each node as a single attribute or a set of independent attributes, without realizing that content inside each node may also have complex structures. In this article, we formulate a new networked graph clustering task where a network contains a set of inter-connected (or networked) super-nodes, each of which is a single-attribute graph. The new super-node representation is applicable to many real-world applications, such as a citation network where each node denotes a paper whose content can be described as a graph, and citation relationships between papers form a networked graph (i.e., a super-graph). Networked graph clustering aims to find similar node groups, each of which contains nodes with similar content and structure information. The main challenge is to properly calculate the similarity between super-nodes for clustering. To solve the problem, we propose to characterize node similarity by integrating structure and content information of each super-node. To measure node content similarity, we use cosine distance by considering overlapped attributes between two super-nodes. To measure structure similarity, we propose an Attributed Random Walk Kernel (ARWK) to calculate the similarity between super-nodes. Detailed node content analysis is also included to build relationships between super-nodes with shared internal structure information, so the structure similarity can be calculated in a precise way. By integrating the structure similarity and content similarity as one matrix, the spectral clustering is used to achieve networked graph clustering. Our method enjoys sound theoretical properties, including bounded similarities and better structure similarity assessment than traditional graph clustering methods. Experiments on real-world applications demonstrate that our method significantly outperforms baseline approaches.

Multi-instance learning (MIL) is useful for tackling labeling ambiguity in learning tasks, by allowing a bag of instances to share one label. Recently, bag mapping methods, which transform a bag to a single instance in a new space via instance selection, have drawn significant attentions. To date, most existing works are developed based on the original space, i.e., utilizing all instances for bag mapping, and instance selection is indirectly tied to the MIL objective. As a result, it is hard to guarantee the distinguish capacity of the selected instances in the new bag mapping space for MIL. In this paper, we propose a direct discriminative mapping approach for multi-instance learning (MILDM), which identifies instances to directly distinguish bags in the new mapping space. Experiments and comparisons on real-world learning tasks demonstrate the algorithm performance.

In this paper we theoretically study the minimum Differentially Resolving Set (DRS) problem derived from the classical sensor placement optimization problem in network source locating. A DRS of a graph G = (V, E) is defined as a subset S ⊆ V where any two elements in V can be distinguished by their different differential characteristic sets defined on S. The minimum DRS problem aims to find a DRS S in the graph G with minimum total weight Σv∈S w(v). In this paper we establish a group of Integer Linear Programming (ILP) models as the solution. By the weighted set cover theory, we propose an approximation algorithm with the Θ(ln n) approximability for the minimum DRS problem on general graphs, where n is the graph size.

In event-based social networks, such as Meetup, social groups refer to self-organized communities that consist of users who share the same interests. In many real-world scenarios, users usually have social group preference and join interested social groups to attend events. It is therefore necessary to consider the influence of social groups to improve the event recommendation performance; however, existing event recommendation models generally consider users' individual preferences and neglect the influence of social groups. To this end, we propose a new Bayesian latent factor model SogBmf that combines social group influence and individual preference for event recommendation. Experiments on real-world data sets demonstrate the effectiveness of the proposed method.

Social recommendation has been widely studied in recent years. Existing social recommendation models use various explicit pieces of social information as regularization terms in recommendation, for instance, social links are considered as new constraints. However, social influence, an implicit source of information in social networks, is seldomly considered, even though it often drives recommendations in social networks. In this paper, we introduce a new global and local influence-based social recommendation model. Based on the observation that user purchase behaviour is influenced by both global influential nodes and the local influential nodes of the user, we formulate the global and local influence as an regularization terms, and incorporate them into a matrix factorization-based recommendation model. Experimental results on large data sets demonstrate the performance of the proposed method.

We formulate a new multi-task graph classification (MTG) problem, where multiple graph classification tasks are jointly regularized to find discriminative subgraphs shared by all tasks for learning. More details can be found in [1].

Social recommendation explores social information to improve the quality of a recommender system. It can be further divided into explicit and implicit social network recommendation. The former assumes the existence of explicit social connections between users in addition to the rating data. The latter one assumes the availability of only the ratings but not the social connections between users since the explicit social information data may not necessarily be available and usually are binary decision values (e.g., whether two people are friends), while the strength of their relationships is missing. Most of the works in this field use only rating data to infer the latent social networks. They ignore the dynamic nature of users that the preferences of users drift over time distinctly. To this end, we propose a new Implicit Dynamic Social Recommendation (IDSR) model, which infers latent social network from cascade data. It can sufficiently mine the information contained in time by mining the cascade data and identify the dynamic changes in the users in time by using the latest updated social network to make recommendations. Experiments and comparisons on three real-world datasets show that the proposed model outperforms the state-of-the-art solutions in both explicit and implicit scenarios.

Most improvements for Naive Bayes (NB) have a common yet important flaw - these algorithms split the modeling of the classifier into two separate stages - the stage of preprocessing (e.g., feature selection and data expansion) and the stage of building the NB classifier. The first stage does not take the NB's objective function into consideration, so the performance of the classification cannot be guaranteed. Motivated by these facts and aiming to improve NB with accurate classification, we present a new learning algorithm called Evolutionary Local Instance Weighted Naive Bayes or ELWNB, to extend NB for classification. ELWNB combines local NB, instance weighted dataset extension and evolutionary algorithms seamlessly. Experiments on 20 UCI benchmark datasets demonstrate that ELWNB significantly outperforms NB and several other improved NB algorithms.

Influence maximization aims to find a set of highly influential nodes in a social network to maximize the spread of influence. The most difficult part of the problem is to estimate the influence spread of any seed set, which has been proved to be #P-hard. There is no efficient method to estimate the influence spread of any seed set till now. Thus, the most common way to obtain the approximate influence spread is Monte Carlo simulation and two popular simulating strategies are applied: one is propagation strategy, the other is snapshot strategy. The former only fits for particular seed set and the latter incurs heavy memory cost. In this paper, we present a new algorithm to estimate the influence spread of any seed set. Our algorithm recursively estimates the influence spread using reachable probabilities from node to node. Accordingly, we provide three strategies to start the recursion by integrating the memory cost and computing efficiency. Experiments demonstrate high performance of our influence estimation.

Deep learning has become increasingly popular in both academic and industrial areas in the past years. Various domains including pattern recognition, computer vision, and natural language processing have witnessed the great power of deep networks. However, current studies on deep learning mainly focus on data sets with balanced class labels, while its performance on imbalanced data is not well examined. Imbalanced data sets exist widely in real world and they have been providing great challenges for classification tasks. In this paper, we focus on the problem of classification using deep network on imbalanced data sets. Specifically, a novel loss function called mean false error together with its improved version mean squared false error are proposed for the training of deep networks on imbalanced data sets. The proposed method can effectively capture classification errors from both majority class and minority class equally. Experiments and comparisons demonstrate the superiority of the proposed approach compared with conventional methods in classifying imbalanced data sets on deep neural networks.

An information cascade occurs when a person observes the actions of others and then engages in the same acts. Cascades may break out if a large population of nodes in the network get affected. The outbreaks of cascades will often bring influential events, which leads to an open research problem: how to accurately predict the cascading outbreaks in social networks? Although there have been some existing works on cascading outbreak prediction, they ignore the structure information of cascades. In this paper, we propose to use subcascades as features for cascade outbreak prediction. We use frequent sequential pattern mining to extract subcascades and then propose a max-margin based classifier to select at most B features for prediction. The proposed model is empirically evaluated on both synthetic and real-world networks. Experimental results demonstrate the effectiveness of the proposed model.

In order to better model complex real-world data and to develop robust features that capture relevant information, we usually employ unsupervised feature learning to learn a layer of features representations from unlabeled data. However, developing domain-specific features for each task is expensive, time-consuming and requires expertise of the data. In this paper, we introduce multi-instance clustering and graphical learning to unsupervised transfer learning. For a better clustering efficient, we proposed a set of algorithms on the application of traffic data learning, instance feature representation, distance calculation of multi-instance clustering, multi-instance graphical cluster initialisation, multi-instance multi-cluster update, and graphical multi-instance transfer clustering (GMITC). In the end of this paper, we examine the proposed algorithms on the Eastwest datasets by couples of baselines. The experiment results indicate that our proposed algorithms can get higher clustering accuracy and much higher programming speed.

Graph classification aims to learn models to classify structure data. To date, all existing graph classification methods are designed to target one single learning task and require a large number of labeled samples for learning good classification models. In reality, each real-world task may only have a limited number of labeled samples, yet multiple similar learning tasks can provide useful knowledge to benefit all tasks as a whole. In this paper, we formulate a new multi-task graph classification (MTG) problem, where multiple graph classification tasks are jointly regularized to find discriminative subgraphs shared by all tasks for learning. The niche of MTG stems from the fact that with a limited number of training samples, subgraph features selected for one single graph classification task tend to overfit the training data. By using additional tasks as evaluation sets, MTG can jointly regularize multiple tasks to explore high quality subgraph features for graph classification. To achieve this goal, we formulate an objective function which combines multiple graph classification tasks to evaluate the informativeness score of a subgraph feature. An iterative subgraph feature exploration and multi-task learning process is further proposed to incrementally select subgraph features for graph classification. Experiments on real-world multi-task graph classification datasets demonstrate significant performance gain.

Extreme Learning Machine (ELM) is an elegant technique for training Single-hidden Layer Feedforward Networks (SLFNs) with extremely fast speed that attracts significant interest recently. One potential weakness of ELM is the random generation of the input weights and hidden biases, which may deteriorate the classification accuracy. In this paper, we propose a new Memetic Algorithm (MA) based Extreme Learning Machine (M-ELM) for classification problems. M-ELM uses Memetic Algorithm which is a combination of population-based global optimization technique and individual-based local heuristic search method to find optimal network parameters for ELM. The optimized network parameters will enhance the classification accuracy and generalization performance of ELM. Experiments and comparisons on 22 benchmark data sets demonstrate that M-ELM is able to provide highly competitive results compared with other state-of-the-art varieties of ELM algorithms.

Many applications involve stream data with structural dependency, graph representations, and continuously increasing volumes. For these applications, it is very common that their class distributions are imbalanced with minority (or positive) samples being only a small portion of the population, which imposes significant challenges for learning models to accurately identify minority samples. This problem is further complicated with the presence of noise, because they are similar to minority samples and any treatment for the class imbalance may falsely focus on the noise and result in deterioration of accuracy. In this paper, we propose a classification model to tackle imbalanced graph streams with noise. Our method, graph ensemble boosting, employs an ensemble-based framework to partition graph stream into chunks each containing a number of noisy graphs with imbalanced class distributions. For each individual chunk, we propose a boosting algorithm to combine discriminative subgraph pattern selection and model learning as a unified framework for graph classification. To tackle concept drifting in graph streams, an instance level weighting mechanism is used to dynamically adjust the instance weight, through which the boosting framework can emphasize on difficult graph samples. The classifiers built from different graph chunks form an ensemble for graph stream classification. Experiments on real-life imbalanced graph streams demonstrate clear benefits of our boosting design for handling imbalanced noisy graph stream.

In this paper, we formulate a novel graph-based learning problem, multi-graph classification (MGC), which aims to learn a classifier from a set of labeled bags each containing a number of graphs inside the bag. A bag is labeled positive, if at least one graph in the bag is positive, and negative otherwise. Such a multi-graph representation can be used for many real-world applications, such as webpage classification, where a webpage can be regarded as a bag with texts and images inside the webpage being represented as graphs. This problem is a generalization of multi-instance learning (MIL) but with vital differences, mainly because instances in MIL share a common feature space whereas no feature is available to represent graphs in a multi-graph bag. To solve the problem, we propose a boosting based multi-graph classification framework (bMGC). Given a set of labeled multi-graph bags, bMGC employs dynamic weight adjustment at both bag- and graph-levels to select one subgraph in each iteration as a weak classifier. In each iteration, bag and graph weights are adjusted such that an incorrectly classified bag will receive a higher weight because its predicted bag label conflicts to the genuine label, whereas an incorrectly classified graph will receive a lower weight value if the graph is in a positive bag (or a higher weight if the graph is in a negative bag). Accordingly, bMGC is able to differentiate graphs in positive and negative bags to derive effective classifiers to form a boosting model for MGC. Experiments and comparisons on real-world multi-graph learning tasks demonstrate the algorithm performance.

Graph classification has drawn great interests in recent years due to the increasing number of applications involving objects with complex structure relationships. To date, all existing graph classification algorithms assume, explicitly or implicitly, that misclassifying instances in different classes incurs an equal amount of cost (or risk), which is often not the case in real-life applications (where misclassifying a certain class of samples, such as diseased patients, is subject to more expensive costs than others). Although cost-sensitive learning has been extensively studied, all methods are based on data with instance-feature representation. Graphs, however, do not have features available for learning and the feature space of graph data is likely infinite and needs to be carefully explored in order to favor classes with a higher cost. In this paper, we propose, CogBoost, a fast cost-sensitive graph classification algorithm, which aims to minimize the misclassification costs (instead of the errors) and achieve fast learning speed for large scale graph data sets. To minimize the misclassification costs, CogBoost iteratively selects the most discriminative subgraph by considering costs of different classes, and then solves a linear programming problem in each iteration by using Bayes decision rule based optimal loss function. In addition, a cutting plane algorithm is derived to speed up the solving of linear programs for fast learning on large scale data sets. Experiments and comparisons on real-world large graph data sets demonstrate the effectiveness and the efficiency of our algorithm.

In traditional multi-instance learning (MIL), instances are typically represented by using a single feature view. As MIL becoming popular in domain specific learning tasks, aggregating multiple feature views to represent multi-instance bags has recently shown promising results, mainly because multiple views provide extra information for MIL tasks. Nevertheless, multiple views also increase the risk of involving redundant views and irrelevant features for learning. In this paper, we formulate a new cross-view feature selection problem that aims to identify the most representative features across all feature views for MIL. To achieve the goal, we design a new optimization problem by integrating both multi-view representation and multi-instance bag constraints. The solution to the objective function will ensure that the identified top-m features are the most informative ones across all feature views. Experiments on two real-world applications demonstrate the performance of the cross-view feature selection for content-based image retrieval and social media content recommendation.

Graph classification has traditionally focused on graphs generated from a single feature view. In many applications, it is common to have useful information from different channels/views to describe objects, which naturally results in a new representation with multiple graphs generated from different feature views being used to describe one object. In this paper, we formulate a new Multi-Graph-View learning task for graph classification, where each object to be classified contains graphs from multiple graph-views. This problem setting is essentially different from traditional single-graph-view graph classification, where graphs are from one single feature view. To solve the problem, we propose a Cross Graph-View Sub graph Feature based Learning (gCGVFL) algorithm that explores an optimal set of sub graphs, across multiple graph-views, as features to represent graphs. Specifically, we derive an evaluation criterion to estimate the discriminative power and the redundancy of sub graph features across all views, and assign proper weight values to each view to indicate its importance for graph classification. The iterative cross graph-view sub graph scoring and graph-view weight updating form a closed loop to find optimal sub graphs to represent graphs for multi-graph-view learning. Experiments and comparisons on real-world tasks demonstrate the algorithm's performance.

A Bayesian Network (BN) is a graphical model which can be used to represent conditional dependency between random variables, such as diseases and symptoms. A Bayesian Network Classifier (BNC) uses BN to characterize the relationships between attributes and the class labels, where a simplified approach is to employ a conditional independence assumption between attributes and the corresponding class labels, i.e., the Naive Bayes (NB) classification model. One major approach to mitigate NB's primary weakness (the conditional independence assumption) is the attribute weighting, and this type of approach has been proved to be effective for NB with simple structure. However, for weighted BNCs involving complex structures, in which attribute weighting is embedded into the model, there is no existing study on whether the weighting will work for complex BNCs and how effective it will impact on the learning of a given task. In this paper, we first survey several complex structure models for BNCs, and then carry out experimental studies to investigate the effectiveness of the attribute weighting strategies for complex BNCs, with a focus on Hidden Naive Bayes (HNB) and Averaged One-Dependence Estimation (AODE). Our studies use classification accuracy (ACC), area under the ROC curve ranking (AUC), and conditional log likelihood (CLL), as the performance metrics. Experiments and comparisons on 36 benchmark data sets demonstrate that attribute weighting technologies just slightly outperforms unweighted complex BNCs with respect to the ACC and AUC, but significant improvement can be observed using CLL.

Naive Bayes (NB) network is a popular classification technique for data mining and machine learning. Many methods exist to improve the performance of NB by overcoming its primary weakness - the assumption that attributes are conditionally independent given the class, using techniques such as backwards sequential elimination and lazy elimination. Some weighting technologies, including attribute weighting and instance weighting, have also been proposed to improve the accuracy of NB. In this paper, we propose a dual weighted model, namely DWNB, for NB classification. In DWNB, we firstly employ an instance similarity based method to weight each training instance. After that, we build an attribute weighted model based on the new training data, where the calculation of the probability value is based on the embedded instance weights. The dual instance and attribute weighting allows DWNB to tackle the conditional independence assumption for accurate classification. Experiments and comparisons on 36 benchmark data sets demonstrate that DWNB outperforms existing weighted NB algorithms.

In this paper, we formulate a new multi-graph learning task with only positive and unlabeled bags, where labels are only available for bags but not for individual graphs inside the bag. This problem setting raises significant challenges because bag-of-graph setting does not have features to directly represent graph data, and no negative bags exits for deriving discriminative classification models. To solve the challenge, we propose a puMGL learning framework which relies on two iteratively combined processes for multigraph learning: (1) deriving features to represent graphs for learning; and (2) deriving discriminative models with only positive and unlabeled graph bags. For the former, we derive a subgraph scoring criterion to select a set of informative subgraphs to convert each graph into a feature space. To handle unlabeled bags, we assign a weight value to each bag and use the adjusted weight values to select most promising unlabeled bags as negative bags. A margin graph pool (MGP), which contains some representative graphs from positive bags and identified negative bags, is used for selecting subgraphs and training graph classifiers. The iterative subgraph scoring, bag weight updating, and MGP based graph classification forms a closed loop to find optimal subgraphs and most suitable unlabeled bags for multi-graph learning. Experiments and comparisons on real-world multigraph data demonstrate the algorithm performance.

This paper formulates a multi-graph learning task. In our problem setting, a bag contains a number of graphs and a class label. A bag is labeled positive if at least one graph in the bag is positive, and negative otherwise. In addition, the genuine label of each graph in a positive bag is unknown, and all graphs in a negative bag are negative. The aim of multi-graph learning is to build a learning model from a number of labeled training bags to predict previously unseen test bags with maximum accuracy. This problem setting is essentially different from existing multi-instance learning (MIL), where instances in MIL share well-defined feature values, but no features are available to represent graphs in a multi-graph bag. To solve the problem, we propose a Multi-Graph Feature based Learning (gMGFL) algorithm that explores and selects a set of discriminative subgraphs as features to transfer each bag into a single instance, with the bag label being propagated to the transferred instance. As a result, the multi-graph bags form a labeled training instance set, so generic learning algorithms, such as decision trees, can be used to derive learning models for multi-graph classification. Experiments and comparisons on real-world multi-graph tasks demonstrate the algorithm performance.

Multi-instance learning concerns about building learning models from a number of labeled instance bags, where each bag consists of instances with unknown labels. A bag is labeled positive if one or more multiple instances inside the bag is positive, and negative otherwise. For all existing multi-instance learning algorithms, they are only applicable to the setting where instances in each bag are represented by a set of well defined feature values. In this paper, we advance the problem to a multi-instance multi-graph setting, where a bag contains a number of instances and graphs in pairs, and the learning objective is to derive classification models from labeled bags, containing both instances and graphs, to predict previously unseen bags with maximum accuracy. To achieve the goal, the main challenge is to properly represent graphs inside each bag and further take advantage of complementary information between instance and graph pairs for learning. In the paper, we propose a Dual Embedding Multi-Instance Multi-Graph Learning (DE-MIMG) algorithm, which employs a dual embedding learning approach to (1) embed instance distributions into the informative sub graphs discovery process, and (2) embed discovered sub graphs into the instance feature selection process. The dual embedding process results in an optimal representation for each bag to provide combined instance and graph information for learning. Experiments and comparisons on real-world multi-instance multi-graph learning tasks demonstrate the algorithm performance.

Probability estimation from a given set of training examples is crucial for learning Naive Bayes (NB) Classifiers. For an insufficient number of training examples, the estimation will suffer from the zero-frequency problem which does not allow NB classifiers to classify instances whose conditional probabilities are zero. Laplace-estimate and M-estimate are two common methods which alleviate the zero-frequency problem by adding some fixed terms to the probability estimation to avoid zero conditional probability. A major issue with this type of design is that the fixed terms are pre-specified without considering the uniqueness of the underlying training data. In this paper, we propose an Artificial Immune System (AIS) based self-adaptive probability estimation method, namely AISENB, which uses AIS to automatically and self-adaptively select the optimal terms and values for probability estimation. The unique immune system based evolutionary computation process, including initialization, clone, mutation, and crossover, ensure that AISENB can adjust itself to the data without explicit specification of functional or distributional forms for the underlying model. Experimental results and comparisons on 36 benchmark datasets demonstrate that AISENB significantly outperforms traditional probability estimation based Naive Bayes classification approaches.

Naive Bayes (NB) is a popularly used classification method. One potential weakness of NB is the strong conditional independence assumption between attributes, which may deteriorate the classification accuracy. In this paper, we propose a new Artificial Immune System based Weighted Naive Bayes (AISWNB) classifier. AISWNB uses immunity theory in artificial immune systems to find optimal weight values for each attribute. The adjusted weight values will alleviate the conditional independence assumption and help calculate the conditional probability in an accurate way. Because AISWNB uses artificial immune system search mechanism to find optimal weights, it does not need to know the importance of individual attributes nor the relevance among attributes. As a result, it can obtain optimal weight value for each attribute during the learning process. Experiments and comparisons on 36 benchmark data sets demonstrate that AISWNB outperforms other state-of-the-art attribute weighted NB algorithms.