Large Language Models (LLMs) often produce fluent but factually incorrect responses, a phenomenon known as hallucination. Abstention, where the model chooses not to answer and instead outputs phrases such as "I don't know", is a common safeguard. However, existing abstention methods typically rely on post-generation signals, such as generation variations or feedback, which limits their ability to prevent unreliable responses in advance. In this paper, we introduce Aspect-Based Causal Abstention (ABCA), a new framework that enables early abstention by analysing the internal diversity of LLM knowledge through causal inference. This diversity reflects the multifaceted nature of parametric knowledge acquired from various sources, representing diverse aspects such as disciplines, legal contexts, or temporal frames. ABCA estimates causal effects conditioned on these aspects to assess the reliability of knowledge relevant to a given query. Based on these estimates, we enable two types of abstention: Type-1, where aspect effects are inconsistent (knowledge conflict), and Type-2, where aspect effects consistently support abstention (knowledge insufficiency). Experiments on standard benchmarks demonstrate that ABCA improves abstention reliability, achieves state-of-the-art performance, and enhances the interpretability of abstention decisions.

Machine unlearning aims to eliminate the influence of specific data from trained models to ensure privacy compliance. However, most existing methods assume full access to the original training dataset, which is often impractical. We address a more realistic yet challenging setting: few-shot zero-glance, where only a small subset of the retained data is available and the forget set is entirely inaccessible. We introduce GFOES, a novel framework comprising a Generative Feedback Network (GFN) and a two-phase fine-tuning procedure. GFN synthesises Optimal Erasure Samples (OES), which induce high loss on target classes, enabling the model to forget class-specific knowledge without access to the original forget data, while preserving performance on retained classes. The two-phase fine-tuning procedure enables aggressive forgetting in the first phase, followed by utility restoration in the second. Experiments on three image classification datasets demonstrate that GFOES achieves effective forgetting at both logit and representation levels, while maintaining strong performance using only 5% of the original data. Our framework offers a practical and scalable solution for privacy-preserving machine learning under data-constrained conditions.

Meme is an expressive medium that often conveys rich emotions and intentions. Recent studies have confirmed the critical role of metaphors in meme understanding. However, existing metaphor research heavily relies on manual annotations, and mainstream vision-language models (VLMs) still struggle with the recognition and comprehension of metaphors. To address these challenges, we introduce MetaGPT, the first vision-language model specifically designed for meme metaphor understanding. MetaGPT is capable of identifying and extracting metaphors in memes, and generating accurate meme interpretations. Furthermore, we construct a dedicated dataset for meme understanding, MUnd, which comprises approximately 32,000 high-quality question-answer (QA) pairs across three core tasks: metaphor detection, metaphor domain extraction, and meme interpretation. Based on MUnd, we further propose an evaluation benchmark for meme understanding and conduct a comprehensive assessment of existing VLMs. Experimental results reveal that current models still face challenges in metaphor comprehension, while MetaGPT consistently outperforms them across all tasks, highlighting its potential in advancing meme understanding.

In social recommenders, the inherent nonlinearity and opacity of synergistic effects across multiple social networks hinders users from understanding how diverse information is leveraged for recommendations, consequently diminishing explainability. However, existing explainers can only identify the topological information in social networks that significantly influences recommendations, failing to further explain the synergistic effects among this information. Inspired by existing findings that synergistic effects enhance mutual information between inputs and predictions to generate information gain, we extend this discovery to graph data. We quantify graph information gain to identify subgraphs embodying synergistic effects. Based on the theoretical insights, we propose SemExplainer, which explains synergistic effects by identifying subgraphs that embody them. SemExplainer first extracts explanatory subgraphs from multi-view social networks to generate preliminary importance explanations for recommendations. A conditional entropy optimization strategy to maximize information gain is developed, thereby further identifying subgraphs that embody synergistic effects from explanatory subgraphs. Finally, SemExplainer searches for paths from users to recommended items within the synergistic subgraphs to generate explanations for the recommendations. Extensive experiments on three datasets demonstrate the superiority of SemExplainer over baseline methods, providing superior explanations of synergistic effects. The implementation is available at https://github.com/yushuowiki/SemExplainer.

Graph Transformers (GTs) are increasingly applied to social network analysis, yet their deployment is often constrained by fairness concerns. This issue is particularly critical in incomplete social networks, where sensitive attributes are frequently missing due to privacy and ethical restrictions. Existing solutions commonly generate these incomplete attributes, which may introduce additional biases and further compromise user privacy. To address this challenge, FairGE (Fair Graph Encoding) is introduced as a fairness-aware framework for GTs in incomplete social networks. Instead of generating sensitive attributes, FairGE encodes fairness directly through spectral graph theory. By leveraging the principal eigenvector to represent structural information and padding incomplete sensitive attributes with zeros to maintain independence, FairGE ensures fairness without data reconstruction. Theoretical analysis demonstrates that the method suppresses the influence of non-principal spectral components, thereby enhancing fairness. Extensive experiments on seven real-world social network datasets confirm that FairGE achieves at least a 16% improvement in both statistical parity and equality of opportunity compared with state-of-the-art baselines.

Pregnancy complications are a leading cause of maternal and neonatal mortality worldwide. Understanding their underlying mechanisms is hindered by dispersed evidence across thousands of studies and complex biological interactions. We present PregBase, a comprehensive knowledge base for pregnancy research comprising automated extraction, validation, and exploration. PregBase was constructed by utilising large language models (LLMs) to extract relationships from literature; 13 LLMs were benchmarked across seven prompting strategies, with ensemble shuffle prompting outperforming single-strategy alternatives. A three-tier validation pipeline combining ontology mapping, graph neural networks, and statistical analysis produced PregKG, a knowledge graph containing 64,087 associations between 13,303 biomedical entities spanning 155 semantic types and 50 vocabularies across 8 relationship types from 8420 articles. Link prediction validated PregBase's inference capability beyond extracted knowledge, recovering established clinical interventions, reconstructing canonical hormonal pathways across maternal-placental-fetal compartments, and identifying novel biomarker candidates for preterm birth, gestational diabetes, and preeclampsia, supported by genetic and expression databases. An interactive web interface (https://pregknowledgebase.com) has been created to enable further exploration via conversational queries. This work provides a scalable foundation for systematic discovery in maternal health research.

ABSTRACT To celebrate the 50th Anniversary of the Information Systems Journal, we are delighted to share our research reflections on the article “Community-diversified influence maximization in social networks” published at Information Systems in 2020. Our reflections will highlight the impact of this article on the authors’ research trajectories, its influence on the broader research community, and its contributions to industry practice.

Fairness-aware federated graph neural networks (FedGNNs) necessitate consideration of both the server and the clients. However, fairness-aware methods struggle to enhance dual-perspective (i.e., server and clients) fairness without sacrificing utility due to the distributed learning framework. As a consequence, the utility sacrifices of fairness-aware graph learning methods are even exacerbated in federated frameworks. In this work we propose F3GL, a dual-perspective fairness federated graph learning method that enhances both global (for the server) and local fairness (for clients) while preserving utility. Through theoretical analysis, we delineate the similarity between original sensitive features and those after convolution under different spectra. Our findings reveal that only the principal eigenvalue contributes to enhancing this similarity. Moreover, our theoretical analysis applies universally to both clients and servers. Specifically, employing a specialized eigenvalue selection strategy allows for effective optimization of both local and global fairness. Drawing on these insights, we improve dual-perspective fairness through the lens of spectral graph theory without sacrificing utility. Experimental results on two real-world datasets show the superiority of F3GL over existing baselines.

To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information Pursuit (VIP) offers an interpretable-by-design framework by sequentially querying input images for human-understandable concepts, using their presence or absence to make predictions. However, existing V-IP methods overlook sample-specific uncertainty in concept predictions, which can arise from ambiguous features or model limitations, leading to suboptimal query selection and reduced robustness. In this paper, we propose an interpretable and uncertainty-aware framework for medical imaging that addresses these limitations by accounting for upstream uncertainties in concept-based, interpretable-by-design models. Specifically, we introduce two uncertainty-aware models, EUAV-IP and IUA-VIP, that integrate uncertainty estimates into the V-IP querying process to prioritize more reliable concepts per sample. EUAV-IP skips uncertain concepts via masking, while IUAV-IP incorporates uncertainty into query selection implicitly for more informed and clinically aligned decisions. Our approach allows models to make reliable decisions based on a subset of concepts tailored to each individual sample, without human intervention, while maintaining overall interpretability. We evaluate our methods on five medical imaging datasets across four modalities: dermoscopy, X-ray, ultrasound, and blood cell imaging. The proposed IUAV-IP model achieves state-of-the-art accuracy among interpretable-by-design approaches on four of the five datasets, and generates more concise explanations by selecting fewer yet more informative concepts. These advances enable more reliable and clinically meaningful outcomes, enhancing model trustworthiness and supporting safer AI deployment in healthcare. Our code and models are available at: https://github.com/Nahiduzzaman09/ UAV-IP.

Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility across various graph-related tasks. This survey provides an in-depth review of recent progress and challenges in graph transformer research. We begin with foundational concepts of graphs and transformers. We then explore design perspectives of graph transformers, focusing on how they integrate graph inductive biases and graph attention mechanisms into the transformer architecture. Furthermore, we propose a taxonomy classifying graph transformers based on depth, scalability, and pretraining strategies, summarizing key principles for effective development of graph transformer models. Beyond technical analysis, we discuss the applications of graph transformer models for node-level, edge-level, and graph-level tasks, exploring their potential in other application scenarios as well. Finally, we identify remaining challenges in the field, such as scalability and efficiency, generalization and robustness, interpretability and explainability, dynamic and complex graphs, as well as data quality and diversity, charting future directions for graph transformer research.

Graphs are prevalent in numerous real-world applications. Previous methods directly model graph structures and achieve significant success. However, these methods encounter bottlenecks due to the inherent irregularity of graphs. An innovative solution is converting graphs into textual representations, thereby harnessing the powerful capabilities of Large Language Models (LLMs) to process and comprehend graphs. In this article, we present a comprehensive review of methodologies for applying LLMs to graphs, termed LLM4graph. The core of LLM4graph lies in transforming graphs into texts for LLMs to understand and analyze. Thus, we propose a novel taxonomy of LLM4graph methods from the view of the transformation. Specifically, existing methods can be divided into two paradigms: Graph2text and Graph2token, which transform graphs into texts or tokens as the input of LLMs, respectively. We point out four challenges during the transformation to systematically present existing methods from a problem-oriented perspective. For practical concerns, we provide a guideline for researchers on selecting appropriate models and LLMs for different graphs and hardware constraints. To empirically evaluate our taxonomy and different technical choices, we conduct experiments with representative methods in Graph2text and Graph2token. We also identify five future research directions for LLM4graph.

Recent studies have highlighted significant fairness issues in Graph Transformer (GT) models, particularly against subgroups defined by sensitive features. Additionally, GTs are computationally intensive and memory-demanding, limiting their application to large-scale graphs. Our experiments demonstrate that graph partitioning can enhance the fairness of GT models while reducing computational complexity. To understand this improvement, we conducted a theoretical investigation into the root causes of fairness issues in GT models. We found that the sensitive features of higher-order nodes disproportionately influence lower-order nodes, resulting in sensitive feature bias. We propose Fairness-aware scalable GT based on Graph Partitioning (FairGP), which partitions the graph to minimize the negative impact of higher-order nodes. By optimizing attention mechanisms, FairGP mitigates the bias introduced by global attention, thereby enhancing fairness. Extensive empirical evaluations on six real-world datasets validate the superior performance of FairGP in achieving fairness compared to state-of-the-art methods.

Senqi Yang, Dongyu Zhang, Jing Ren, Ziqi Xu, Xiuzhen Zhang, Yiliao Song, Hongfei Lin, Feng Xia. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large Language Models (LLMs) have shown impressive capabilities in natural language processing but still struggle to perform well on knowledge-intensive tasks that require deep reasoning and the integration of external knowledge. Although methods such as Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) have been proposed to enhance LLMs with external knowledge, they still suffer from internal bias in LLMs, which often leads to incorrect answers. In this paper, we propose a novel causal prompting framework, Conditional Front-Door Prompting (CFD-Prompting), which enables the unbiased estimation of the causal effect between the query and the answer, conditional on external knowledge, while mitigating internal bias. By constructing counterfactual external knowledge, our framework simulates how the query behaves under varying contexts, addressing the challenge that the query is fixed and is not amenable to direct causal intervention. Compared to the standard front-door adjustment, the conditional variant operates under weaker assumptions, enhancing both robustness and generalisability of the reasoning process. Extensive experiments across multiple LLMs and benchmark datasets demonstrate that CFD-Prompting significantly outperforms existing baselines in both accuracy and robustness.

Comprehensible neural network explanations are foundations for a better understanding of decisions, especially when the input data are infused with malicious perturbations. Existing solutions generally mitigate the impact of perturbations through adversarial training, yet they fail to generate comprehensible explanations under unknown perturbations. To address this challenge, we propose AGAIN, a factor graph-based interpretable neural network, which is capable of generating comprehensible explanations under unknown perturbations. Instead of retraining like previous solutions, the proposed AGAIN directly integrates logical rules by which logical errors in explanations are identified and rectified during inference. Specifically, we construct the factor graph to express logical rules between explanations and categories. By treating logical rules as exogenous knowledge, AGAIN can identify incomprehensible explanations that violate real-world logic. Furthermore, we propose an interactive intervention switch strategy rectifying explanations based on the logical guidance from the factor graph without learning perturbations, which overcomes the inherent limitation of adversarial training-based methods in defending only against known perturbations. Additionally, we theoretically demonstrate the effectiveness of employing factor graph by proving that the comprehensibility of explanations is strongly correlated with factor graph. Extensive experiments are conducted on three datasets and experimental results illustrate the superior performance of AGAIN compared to state-of-the-art baselines.

State-of-the-art brain graph analysis methods fail to fully encode the small-world architecture of brain graphs (accompanied by the presence of hubs and functional modules), and therefore lack biological plausibility to some extent. This limitation hinders their ability to accurately represent the brain's structural and functional properties, thereby restricting the effectiveness of machine learning models in tasks such as brain disorder detection. In this work, we propose a novel Biologically Plausible Brain Graph Transformer (BioBGT) that encodes the small-world architecture inherent in brain graphs. Specifically, we present a network entanglement-based node importance encoding technique that captures the structural importance of nodes in global information propagation during brain graph communication, highlighting the biological properties of the brain structure. Furthermore, we introduce a functional module-aware self-attention to preserve the functional segregation and integration characteristics of brain graphs in the learned representations. Experimental results on three benchmark datasets demonstrate that BioBGT outperforms state-of-the-art models, enhancing biologically plausible brain graph representations for various brain graph analytical tasks

Early detection of Alzheimer's disease (AD) through spontaneous speech analysis represents a promising, non-invasive diagnostic approach. Existing methods predominantly rely on fusion-based multimodal deep learning, effectively integrating linguistic and acoustic features. However, these methods inadequately model higher-order interactions between modalities, reducing diagnostic accuracy. To address this, we introduce SpeechHGT, a multimodal hypergraph transformer designed to capture and learn higher-order interactions in spontaneous speech features. SpeechHGT encodes multimodal features as hypergraphs, where nodes represent individual features and hyperedges represent grouped interactions. A novel hypergraph attention mechanism enables robust modeling of both pairwise and higher-order interactions. Experimental evaluations on the DementiaBank datasets reveal that SpeechHGT achieves state-of-the-art performance, surpassing baseline models in accuracy and F1 score. These results highlight the potential of hypergraph-based models to improve AI-driven diagnostic tools for early AD detection.

With the development of wearable cardiac ultrasound devices, it is no longer sufficient to solely rely on doctors for diagnosing long-term echocardiogram videos. Automated diagnosis of echocardiogram videos has now become a research hotspot. Existing studies only analyze echocardiogram video through discriminative models, which have limited question-answering capabilities. Therefore, this study innovatively proposes a large language model with cardiac ultrasound diagnostic capabilities—EchoGPT. EchoGPT integrates the robust communication and comprehension capabilities of large language models (LLMs) with the diagnostic prowess of traditional medical models, empowering patients to obtain accurate medical indicator data and comprehend their health conditions through interactive questioning with the model. The model is capable of local deployment on personal computers, effectively safe guarding user privacy. EchoGPT operates through three main components: left ventricle segmentation, left ventricular ejection fraction LVEF prediction, and finetuning of video-text LLMs. Experimental results demonstrate EchoGPT’s superior accuracy in predicting LVEF compared to other models, and positive feedback from professional physicians through questionnaire surveys, validating its potential in practical applications. The demo is available at https://github.com/zhuqh19/EchoGPT.

The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning (CL), which updates models using a limited set of old data samples, helps preserve prior knowledge while incorporating new information. However, existing rehearsal techniques don't effectively capture the diversity of audio characteristics, introducing bias and increasing the risk of forgetting. To address this challenge, we propose Rehearsal with Auxiliary-Informed Sampling (RAIS), a rehearsal-based CL approach for audio deepfake detection. RAIS employs a label generation network to produce auxiliary labels, guiding diverse sample selection for the memory buffer. Extensive experiments show RAIS outperforms state-of-the-art methods, achieving an average Equal Error Rate (EER) of 1.953 % across five experiences. The code is available at: https://github.com/falihgoz/RAIS.

Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are unsuitable for embedded robotic devices with limited resources (such as intelligent vehicles/cars) where rapid detection is necessary to prevent accidents. This paper introduces LiteFat, a lightweight spatio-temporal graph learning model designed to detect driver fatigue efficiently while maintaining high accuracy and low computational demands. LiteFat involves converting streaming video data into spatio-temporal graphs (STG) using facial landmark detection, which focuses on key motion patterns and reduces unnecessary data processing. LiteFat uses MobileNet to extract facial features and create a feature matrix for the STG. A lightweight spatio-temporal graph neural network is then employed to identify signs of fatigue with minimal processing and low latency. Experimental results on benchmark datasets show that LiteFat performs competitively while significantly reduced computational complexity and latency as compared to current state-of-the-art methods. This work advances the development of real-time, resource-efficient human fatigue detection systems that can be implemented upon embedded robotic devices.

Localizing text under low-light conditions has gained attention, with typical approaches relying on two stage cascading modules that combine low-light enhancement and text localization. However, these often require additional enhancement modules and cause inefficiency in joint optimization. In this work, we address the challenge by adopting a novel approach: tailoring the detector for low light conditions through knowledge distillation from normal light conditions, without relying on any enhancement module. First, we design a Graph Topological Aggregation (GTA) model that utilizes the message passing mechanism of graph neural networks to structurally represent text topology and facilitate structured feature expression in knowledge transfer. We then introduce two specially designed knowledge transfer constraints aimed at enhancing the learning of text's multi-scale features and topological knowledge. Finally,we propose a Stage-wise Bilevel Knowledge Transfer learning strategy that designates the low-light learning process as the upper-level task, while treating normal light learning as the lower-level task, effectively addressing the coupling issues and sequential dependencies prevalent during the distillation process. Extensive experiments underscore the approach's superiority.

Heterogeneous Graph Neural Networks (HGNNs) are extensively applied in modeling web-based applications that involve heterogeneous graph structures. Explanation models for HGNNs aim to address their ''black box'' nature. Enhancing the interpretability of HGNNs leads to a better understanding and can potentially improve predictive performance. However, existing post-hoc HGNN explanation methods cannot impact the HGNN's predictions. Self-explainable homogeneous models also perform poorly on heterogeneous graphs. To address these challenges, we present a Self-Explainable Heterogeneous Graph Neural Network (SEHG), a novel architecture that integrates explanation generation into the learning process of HGNN through two alternative stages. The first stage focuses on producing high-quality explanations while providing predictions alongside. The second stage enhances prediction accuracy by a contrastive learning strategy. Unlike the current methods that rely on manually defined metapaths for structural explanations, SEHG generates important structure and feature explanations by learnable heterogeneous masks. To ensure high-quality and sparsity explanation, these masks are regulated by a uniquely designed range-based penalty during training. Moreover, we introduce HetBA, a collection of synthetic heterogeneous datasets designed to quantify and visualize explanations or heterogeneous graphs. Extensive experiments demonstrate the effectiveness of SEHG, which surpasses strong baselines in real-world node classification tasks by notable margins of up to 3.91%. SEHG also achieves state-of-the-art performance on synthetic datasets with improvement of up to 9.44%, and records the highest fidelity scores in explanation tasks, improving by up to 46.57%. To our knowledge, SEHG is a pioneering self-explainable HGNN framework that achieves state-of-the-art performance on both heterogeneous graph explanation and prediction tasks.

Knowledge tracing (KT) aims to predict students' future performance based on their past learning activities. However, no one is perfect. Factors such as carelessness, fatigue, and stress often cause students to make mistakes on problems they have already mastered, leading to anomalies in their historical learning data. These anomalies disrupt inherent patterns in the data, misleading the KT model. Extracting cognitive patterns that accurately reflect students' knowledge mastery from such error-prone data remains a significant challenge. Against this background, this paper proposes a novel KT method named RoubstKT, inspired by educational measurement theory and frequency-based decomposition. A cognitive decoupling analyzer is proposed to decouple the student's cognitive pattern and random factors from the data through smoothing and subtraction operations, then recombine them using a gating mechanism or adaptive parameter fusion strategy. To more effectively diagnose students' knowledge mastery, we employ a decay-based attention mechanism that focuses on random behaviors at adjacent time steps. We conducted comprehensive experiments based on real-world datasets and targeted datasets with added random noise. The experimental results demonstrated the effectiveness of the proposed method.

Dynamic graph clustering aims to detect and track time-varying clusters in dynamic graphs, revealing the evolutionary mechanisms of complex real-world dynamic systems. Matrix factorization-based methods are promising approaches for this task; however, these methods often struggle with scalability and can be time-consuming when applied to large-scale dynamic graphs. Moreover, they tend to lack robustness and are vulnerable to real-world noisy data. To address these issues, we make three key contributions. First, to improve scalability, we propose temporal separated matrix factorization, where a single matrix is divided into multiple smaller matrices for independent factorization, resulting in faster computation. Second, to improve robustness, we introduce bi-clustering regularization, which jointly optimizes graph embedding and clustering, thereby filtering out noisy features from the graph embeddings. Third, to further enhance effectiveness and efficiency, we propose selective embedding updating, where we update only the embeddings of dynamic nodes while the embeddings of static nodes are fixed among different timestamps. Experimental results on six synthetic and five real-world benchmarks demonstrate the scalability, robustness and effectiveness of our proposed method. Source code is available at https://github.com/Clearloveyuan/DyG-MF.

Psychiatric disorders involve complex neural activity changes, with functional magnetic resonance imaging (fMRI) data serving as key diagnostic evidence. However, data scarcity and the diverse nature of fMRI information pose significant challenges. While graph-based self-supervised learning (SSL) methods have shown promise in brain network analysis, they primarily focus on time-domain representations, often overlooking the rich information embedded in the frequency domain. To overcome these limitations, we propose F requency- E nhanced Net work (FENet), a novel SSL framework specially designed for fMRI data that integrates time-domain and frequency-domain information to improve psychiatric disorder detection in small-sample datasets. FENet constructs multi-view brain networks based on the inherent properties of fMRI data, explicitly incorporating frequency information into the learning process of representation. Additionally, it employs domain-specific encoders to capture temporal-spectral characteristics, including an efficient frequency-domain encoder that highlights disease-relevant frequency features. Finally, FENet introduces a domain consistency-guided learning objective, which balances the utilization of diverse information and generates frequency-enhanced brain graph representations. Experiments on two real-world medical datasets demonstrate that FENet outperforms state-of-the-art methods while maintaining strong performance in minimal data conditions. Furthermore, we analyze the correlation between various frequency-domain features and psychiatric disorders, emphasizing the critical role of high-frequency information in disorder detection.

Metaphors play a crucial role in human communication, yet their comprehension remains a significant challenge for natural language processing (NLP) due to the cognitive complexity involved. According to Conceptual Metaphor Theory (CMT), metaphors map a target domain onto a source domain, and understanding this mapping is essential for grasping the nature of metaphors. Existing NLP research has focused on tasks like metaphor detection and sentiment analysis. However, there has been limited attention to identifying mappings between source and target domains. Moreover, non-English multimodal metaphor resources remain largely neglected in the literature, hindering a deeper understanding of the key elements involved in metaphor interpretation. To address this gap, we developed a Chinese multimodal metaphor advertisement dataset (namely CM3D) that includes annotations of specific target and source domains. This dataset aims at fostering further research into metaphor comprehension, particularly in non-English languages. Furthermore, we propose a Chain-of-Thought (CoT) Prompting-based Metaphor Mapping Identification Model (CPMMIM), which simulates the human cognitive process for identifying these mappings. Drawing inspiration from CoT reasoning and Bi-Level Optimization (BLO), we treat the task as a hierarchical identification problem, enabling more accurate and interpretable metaphor mapping. Our experimental results demonstrate the effectiveness of CPMMIM, highlighting its potential for advancing metaphor comprehension in NLP. Our dataset and code are both publicly available to encourage further advancements in this field.

Many multivariate time series anomaly detection frameworks have been proposed and widely applied. However, most of these frameworks do not consider intrinsic relationships between variables in multivariate time series data, thus ignoring the causal relationship among variables and degrading anomaly detection performance. This work proposes a novel framework called CGAD, an entropy causal graph for multivariate time series Anomaly Detection. CGAD utilizes transfer entropy to construct graph structures that unveil the underlying causal relationships among time series data. Weighted graph convolutional networks combined with causal convolutions are employed to model both the causal graph structures and the temporal patterns within multivariate time series data. Furthermore, CGAD applies anomaly scoring, leveraging median absolute deviation-based normalization to improve the robustness of the anomaly identification process. Extensive experiments demonstrate that CGAD outperforms state-of-the-art methods on real-world datasets with a 9% average improvement in terms of three different multivariate time series anomaly detection metrics.

Multimodal brain graph transformers have become one of the foundational architectures of graph foundation models for brain science, relying on multimodal brain network fusion. However, most current multimodal brain network fusion methods primarily focus on modality-specific information fusion. The interplays within structural-functional brain networks are often ignored. Therefore, they fail to acquire essential coupling information, which is crucial for obtaining robust joint brain network representations. This oversight inevitably limits the effectiveness and generalization of these representations in various downstream tasks. To this end, we propose a novel joint structural-functional brain graph transformer model (namely sfBGT). Technically, we design a cross-network assortativity quantification mechanism to enable structural-functional brain network coupling, thus capturing the interplays of brain structure and function. We then employ a multimodal graph transformer to effectively learn joint representations of structural-functional brain networks along with their coupling relation representations. Experimental results on three real-world datasets demonstrate the superiority of sfBGT over state-of-the-art baselines.

Dynamic brain networks play a pivotal role in diagnosing brain disorders by capturing temporal changes in brain activity and connectivity. Previous methods often rely on sliding-window approaches for constructing these networks using fMRI data. However, these methods face two key limitations: a fixed temporal length that inadequately captures brain activity dynamics and a global spatial scope that introduces noise and reduces sensitivity to localized dysfunctions. These challenges can lead to inaccurate brain network representations and potential misdiagnoses.To address these challenges, we propose BrainDGT, a dynamic Graph Transformer model designed to enhance the construction and analysis of dynamic brain networks for more accurate diagnosis of brain disorders. BrainDGT leverages adaptive brain states by deconvolving the Hemodynamic Response Function (HRF) within individual functional brain modules to generate dynamic graphs, addressing the limitations of fixed temporal length and global spatial scope. The model learns spatio-temporal local features through attention mechanisms within these graphs and captures global interactions across modules using adaptive fusion. This dual-level integration enhances the model's ability to analyze complex brain connectivity patterns. We validate BrainDGT's effectiveness through classification experiments on three fMRI datasets (ADNI, PPMI, and ABIDE), where it outperforms state-of-the-art methods. By enabling adaptive, localized analysis of dynamic brain networks, BrainDGT advances neuroimaging and supports the development of more precise diagnostic and treatment strategies in biomedical research.

In recent years, deep learning has increasingly gained attention in the field of traffic prediction. Existing traffic prediction models often rely on GCNs or attention mechanisms withO(N2) complexity to dynamically extract traffic node features, which lack efficiency and are not lightweight. Additionally, these models typically only utilize historical data for prediction, without considering the impact of the target information on the prediction. To address these issues, we propose a Pattern-Matching Dynamic Memory Network (PM-DMNet). Unlike traditional attention and graph convolution-based approaches, PM-DMNet employs a novel dynamic memory network that stores the most representative traffic patterns from historical data in a memory matrix through training. It captures traffic pattern features by comparing the similarity between the memory matrix and the current traffic state. This method not only achieves excellent predictive performance but also significantly reduces computational complexity toO(N). The PM-DMNet also introduces two prediction methods: Recursive Multi-step Prediction (RMP) and Parallel Multi-step Prediction (PMP), which leverage the time features of the prediction targets to assist in the prediction process. Furthermore, a transfer attention mechanism is integrated into PMP, transforming historical data features to better align with the predicted target states, thereby capturing trend changes more accurately and reducing errors. Extensive experiments demonstrate the superiority of the proposed model over existing benchmarks. The source codes are available at: https://github.com/wengwenchao123/PM-DMNet

Missing traffic data is a common phenomenon in practice, which has serious implications for the development of downstream data-driven traffic research. Although numerous methods have been proposed to impute missing values, two limitations still exist: lack of complete ground truth and reliance on carefully constructed model structures. In this paper, we propose a novel deep neural imputation network framework named STIseq2seq, based on self-supervised contrastive learning. It follows a sequence-to-sequence architecture with attention mechanism to address the traffic data imputation problem. Specifically, the model consists of two key components: encoder and decoder, both composed of ST-block. Initially, we utilize dynamic graph convolution (DGC) and gated recurrent unit (GRU) to construct the fundamental unit, ST-block, for learning spatiotemporal dependencies. Then, a bidirectional ST-block is employed to model incomplete input data in the encoder; while a forward ST-block combined with an attention mechanism is used to accurately impute missing data in the decoder. Lastly, we devise a training method based on self-supervised contrastive learning, achieved through randomly shuffling the masking matrix, to enhance training effectiveness. Extensive experiments conducted on two available real-world traffic datasets demonstrate that our proposed STIseq2seq has superior and stable performance compared to multiple baseline models under different missing data scenarios with missing rates ranging from 20% to 80%. Visualization analysis of the imputation results further provides insights into the advantages of STIseq2seq.

The primary objective of graph node anomaly detection is to pinpoint rare patterns that display marked deviations from the typical one. Existing methods utilize Graph Convolutional Networks (GCNs) to model complex interactions in Heterogeneous Information Networks (HINs), typically homogenizing HINs using meta-paths to effectively focus on particular semantic scenarios. However, meta-paths excessively emphasize specific nodes and their connections on predefined paths, leading to the neglect of one-hop context-rich neighbors. Furthermore, the conversion from heterogeneous to homogeneous structures disrupts inherent relationships, resulting in an irreversible loss of direct links. Thus, we propose a dual-view-based H eterogeneous I nformation N etworks Node Ano maly Detection framework, HINAno, to mitigate structural loss. HINAno adopts a synergetic approach that balances local structural information with semantic richness, drawing from both the one-hop neighbor view and the meta-path view. Specifically, this dual-view utilizes hierarchical fusion mechanisms at node, type, and semantic levels to capture one-hop and multi-hop neighborhoods in a level-wise manner. In addition, HINAno adopts self-supervised contrastive learning and GCNs to amplify the gap between normal and abnormal nodes, thereby reducing the reliance on anomalous labels and enhancing the capability of anomaly detection. Finally, we successfully verify that the HINAno framework is effective and superior on four real-world datasets.

Generating post hoc causal explanations for graph neural network-based recommender systems is vital for enhancing the credibility and interpretability of recommendations. Existing model-agnostic explainers primarily capture statistical correlations between topological information and recommendation outcomes. However, they often fail to identify true causal relationships due to their model-agnostic design and the challenges posed by heterogeneous graph structures. To address these limitations, we propose a causality-inspired graph neural network explainer for recommender systems, namely CaGE, which generates explanations reflecting causality in recommendation scenarios without accessing the internal parameters of the recommender system. Unlike previous explainers that rely on correlation-based learning, CaGE leverages heterogeneous interventional distributions to eliminate backdoor paths of non-causal variables in the structural causal model of the recommendation task, ensuring causation is accurately captured. Specifically, CaGE incorporates backdoor adjustment based on heterogeneous interventional distributions and causal contrastive learning to optimize a set of heterogeneous soft masks that disentangle causation from non-causation. Additionally, a causality-inspired meta-path search strategy is employed to represent causation as paths between users and recommended items, further enhancing explanation readability. Extensive experiments are conducted on three recommendation datasets, and the experimental results illustrate the superior fidelity of CaGE as compared to state-of-the-art baselines.

The rise of software-defined networking (SDN) has greatly enhanced the flexibility and programmability of networks, but it has also brought new security challenges while achieving more efficient multipath, more flexible load balancing, and more secure authentication. To address this problem, we propose an innovative solution: the load-balanced heterogeneous multipath authenticated routing selection (LBHMARS) framework. This framework implements load balancing of multipath routing, as well as authentication and location of compromised switches in SDN networks, while ensuring the security of traffic entering the system. LBHMARS establishes a secure and efficient routing mechanism in SDN using the IPv6 protocol. We combine strong encryption and signature schemes with a novel path load balancing algorithm to ensure traffic balance and data integrity among multiple network paths. Finally, we introduce a mechanism to locate and isolate malicious switches, further enhancing network security. Compared with existing solutions, our extensive simulations show that LBHMARS has superior performance in mitigating attacks and maintaining high network throughput. In addition, LBHMARS also performs well in terms of latency and low packet loss.

Large language models (LLMs) have been widely used in society due to their amazing emergent capabilities, but they also bring security issues. A large amount of content on the Internet may be generated by AI. Whether it is social forums or more professional academic fields, the abuse of AI has become a problem. Especially in some professional fields, Blindly trusting what the Internet says is dangerous. For this reason, for some fields that are risky and need to limit the use of AI, such as medicine, a more comprehensive benchmark is needed to test the ability of AI-generated text detection tasks. Considering the popularity of LLMs, the data distributions used in the training process of different LLMs may lead to the differences in generated data distributions, especially for some LLMs for non-native English speakers. To address this issue, this article introduces an AI-generated text detection dataset in the field of medical question answering. This dataset is generated by various models and prompting methods, and cross validation is performed on multiple types of data between texts generated by different methods to verify the effectiveness of AI-generated text detection and model classification tasks, and to study the generalization of the dataset in different tasks. We have published the dataset for future research on https://github.com/Hellpoop/MAT.

Emotion recognition in conversation (ERC) is essential for dialogue systems to identify the emotions expressed by speakers. Although previous studies have made significant progress, accurate recognition and interpretation of similar fine-grained emotion properly accounting for individual variability remains a challenge. One particular under-explored area is the role of individual beliefs and desires in modelling emotion. Inspired by the Belief-Desire Theory of Emotion, we propose a novel method for conversational emotion recognition that incorporates both belief and desire to accurately identify emotions. We extract emotion-eliciting events from utterances and construct graphs that represent beliefs and desires in conversations. By applying message passing between nodes, our graph effectively models the utterance context, speaker’s global state, and the interaction between emotional beliefs, desires, and utterances. We evaluate our model’s performance by conducting extensive experiments on four popular ERC datasets and comparing it with multiple state-of-the-art models. The experimental results demonstrate the superiority of our proposed model and validate the effectiveness of each module in the model.

Fairness-aware Graph Neural Networks (GNNs) often face a challenging trade-off, where prioritizing fairness may require compromising utility. In this work, we re-examine fairness through the lens of spectral graph theory, aiming to reconcile fairness and utility within the framework of spectral graph learning. We explore the correlation between sensitive features and spectrum in GNNs, using theoretical analysis to delineate the similarity between original sensitive features and those after convolution under different spectra. Our analysis reveals a reduction in the impact of similarity when the eigenvectors associated with the largest magnitude eigenvalue exhibit directional similarity. Based on these theoretical insights, we propose FUGNN, a novel spectral graph learning approach that harmonizes the conflict between fairness and utility. FUGNN ensures algorithmic fairness and utility by truncating the spectrum and optimizing eigenvector distribution during the encoding process. The fairness-aware eigenvector selection reduces the impact of convolution on sensitive features while concurrently minimizing the sacrifice of utility. FUGNN further optimizes the distribution of eigenvectors through a transformer architecture. By incorporating the optimized spectrum into the graph convolution network, FUGNN effectively learns node representations. Experiments on six real-world datasets demonstrate the superiority of FUGNN over baseline methods. The codes are available at https://github.com/yushuowiki/FUGNN.

In existing graph data, the connection relationships often exhibit uniform weights, leading to the model aggregating neighboring nodes with equal weights across various connection types. However, this uniform aggregation of diverse information diminishes the discriminability of node representations, contributing significantly to the over-smoothing issue in models. In this paper, we propose the Flexible Graph Neural Diffusion (FGND) model, incorporating latent class representation to address the misalignment between graph topology and node features. In particular, we combine latent class representation learning with the inherent graph topology to reconstruct the diffusion matrix during the graph diffusion process. We introduce the sim metric to quantify the degree of mismatch between graph topology and node features. By flexibly adjusting the dependency level on node features through the hyperparameter, we accommodate diverse adjacency relationships. The effective filtering of noise in the topology also allows the model to capture higher order information, significantly alleviating the over-smoothing problem. Meanwhile, we model the graphical diffusion process as a set of differential equations and employ advanced partial differential equation tools to obtain more accurate solutions. Empirical evaluations on five benchmarks reveal that our FGND model outperforms existing popular GNN methods in terms of both overall performance and stability under data perturbations. Meanwhile, our model exhibits superior performance in comparison to models tailored for heterogeneous graphs and those designed to address oversmoothing issues.

Understanding a meme is a challenging task, due to the metaphorical information contained in the meme that requires intricate interpretation to grasp its intended meaning fully. In previous works, attempts have been made to facilitate computational understanding of memes through introducing human-annotated metaphors as extra input features into machine learning models. However, these approaches mainly focus on formulating linguistic representation of a metaphor (extracted from the texts appearing in memes), while ignoring the connection between the metaphor and corresponding visual features (e.g., objects in meme images). In this paper, we argue that a more comprehensive understanding of memes can only be achieved through a joint modelling of both visual and linguistic features of memes. To this end, we propose an approach to generate Multimodal Metaphorical feature for Meme Classification, named MMMC. MMMC derives visual characteristics from linguistic attributes of metaphorical concepts, which more effectively convey the underlying metaphorical concept, leveraging a text-conditioned generative adversarial network. The linguistic and visual features are then integrated into a set of multimodal metaphorical features for classification purpose. We perform extensive experiments on a benchmark metaphorical meme dataset, MET-Meme. Experimental results show that MMMC significantly outperforms existing baselines on the task of emotion classification and intention detection. Our code and dataset are available at https://github.com/liaolianfoka/MMMC.

Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detection, LLE is primarily designed for human vision rather than machine vision and can accumulate errors. In this work, we propose an efficient and effective single-stage approach for localizing text in the dark that circumvents the need for LLE. We introduce a constrained learning module as an auxiliary mechanism during the training stage of the text detector. This module is designed to guide the text detector in preserving textual spatial features amidst feature map resizing, thus minimizing the loss of spatial information in texts under low-light visual degradations. Specifically, we incorporate spatial reconstruction and spatial semantic constraints within this module to ensure the text detector acquires essential positional and contextual range knowledge. Our approach enhances the original text detector's ability to identify text's local topological features using a dynamic snake feature pyramid network and adopts a bottom-up contour shaping strategy with a novel rectangular accumulation technique for accurate delineation of streamlined text features. In addition, we present a comprehensive low-light dataset for arbitrary-shaped text, encompassing diverse scenes and languages. Notably, our method achieves state-of-the-art results on this low-light dataset and exhibits comparable performance on standard normal light datasets. The code and dataset will be released.

Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multi-level communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis.

Federated recommender systems have been crucially enhanced through data sharing and continuous model updates, attributed to the pervasive connectivity and distributed computing capabilities of Internet of Things (IoT) devices. Given the sensitivity of IoT data, transparent data processing in data sharing and model updates is paramount. However, existing methods fall short in tracing the flow of shared data and the evolution of model updates. Consequently, data sharing is vulnerable to exploitation by malicious entities, raising significant data privacy concerns, while excluding data sharing will result in suboptimal recommendations. To mitigate these concerns, we present LIBERATE, a privacy-traceable federated recommender system. We design a blockchain-based traceability mechanism, ensuring data privacy during data sharing and model updates. We further enhance privacy protection by incorporating local differential privacy in user–server communication. Extensive evaluations with the real-world data set corroborate LIBERATE’s capabilities in ensuring data privacy during data sharing and model update while maintaining efficiency and performance. Results underscore blockchain-based traceability mechanism as a promising solution for privacy preserving in federated recommender systems.

Mobile edge computing (MEC) is considered a promising technology to provide low-latency services by keeping computing and other resources physically close to where they are needed. The functions implemented through network function virtualization (NFV) technology in MEC are called virtual network function (VNF) instances, and the deployment and scheduling of VNF instances have always been a hot topic. The deployment refers to deploying instances on the edge servers, while scheduling refers to allocating resources to complete user requests. However, most of the existing works fail to jointly consider the deployment and scheduling of VNF instances, which cannot complete user requests reasonably and efficiently. Besides, the deployment cost can be significantly reduced by making users share the same type of instances instead of assigning one to each user. Therefore, the objective of our article is to investigate the efficient deployment and scheduling of VNF instances that are shared among different users under constraints of user delay and network resources. We first build a VNF instance deployment and scheduling model in MEC networks to study how to minimize cost and maximize network throughput under the constraints of user delay and the computing and storage resources of cloudlets. Then, taking advantage of its sharing feature, we propose a set covering-based efficient deployment and scheduling scheme called SCEDS and evaluate its performance by extensive simulations. The simulation results demonstrate the superiority of our proposed method compared to the existing ones.

Due to the swift advancement of edge computing and mobile crowdsensing (MCS), edge-assisted MCS (EAMCS) has emerged as a promising paradigm, leveraging sensor-embedded mobile devices for the collection and sharing of environmental data. As the sensing scale increases in the modern urban, the application scenario becomes more and more complex, and the budget of users and platform is limited. Therefore, it is indispensable to study the effective task allocation mechanism with considering the multiple budget constraints in the EAMCS system. However, a majority of the existing studies unilaterally focus on either the users’ time budget or the platform’s budget, disregarding the crucial aspect of the users’ energy budget. In this article, we design a joint user movement, sensing, offloading, and computation framework adopting the computation offloading strategy called binary processing strategy. In addition, the multitask data collection with a limited budget (MDCB) problem considering time, energy, and platform budget in EAMCS is formulated, which is proved to be nondeterministic polynomial-hard. In order to maximize the amount of data collected by the users in the MDCB problem, we first verify the submodularity of the objective function, then propose the global maximum data first search algorithm and task sequence-based genetic algorithm to solve the problem. The extensive experiments are conducted on both synthetic and real-world data sets to demonstrate the effectiveness of our proposed schemes.

Automated multi-label chest X-rays (CXR) image classification has achieved substantial progress in clinical diagnosis via utilizing sophisticated deep learning approaches. However, most deep models have high computational demands, which makes them less feasible for compact devices with low computational requirements. To overcome this problem, we propose a knowledge distillation (KD) strategy to create the compact deep learning model for the real-time multi-label CXR image classification. We study different alternatives of CNNs and Transforms as the teacher to distill the knowledge to a smaller student. Then, we employed explainable artificial intelligence (XAI) to provide the visual explanation for the model decision improved by the KD. Our results on three benchmark CXR datasets show that our KD strategy provides the improved performance on the compact student model, thus being the feasible choice for many limited hardware platforms. For instance, when using DenseNet161 as the teacher network, EEEA-Net-C2 achieved an AUC of 83.7%, 87.1%, and 88.7% on the ChestX-ray14, CheXpert, and PadChest datasets, respectively, with fewer parameters of 4.7 million and computational cost of 0.3 billion FLOPS.

Coronavirus disease 2019 (COVID-19) as a global pandemic causes a massive disruption to social stability that threatens human life and the economy. An effective forecasting system is arguably important to provide an early signal of the risk of COVID-19 infection so that the authorities are ready to protect the people from the worst. However, making a good forecasting model for infection risks in different cities or regions is not an easy task, because it has a lot of influential factors that are difficult to be identified manually. To address the current limitations, we propose a deep graph learning model, called PANDORA, to predict the infection risks of COVID-19, by considering all essential factors and integrating them into a geographical network. The framework uses geographical position relationships and transportation frequency as higher order structural properties formulated by higher order network structures (i.e., network motifs). Moreover, four significant node attributes (i.e., multiple features of a particular area, including climate, medical condition, economy, and human mobility) are also considered. We propose three different aggregators to better aggregate node attributes and structural features, namely, Hadamard, Summation, and Connection. Experimental results over real data show that PANDORA outperforms the baseline methods with higher accuracy and faster convergence speed, no matter which aggregator is chosen.

Over the last decade, the Internet of Things (IoT) technology has advanced significantly in a variety of fields. As a pivotal application of IoT, intelligent transportation systems (ITS) have harvested great attention from the research community. Radio frequency identification (RFID) which is an essential technology in IoT plays a key role in ITS to identify tagged vehicles. Unknown tag identification which aims at identifying the existing unknown tags is crucial to monitor the newly entering vehicles in the RFID-assisted intelligent transportation systems. However, the COTS (commercial-off-the-shelf) RFID tags that harvest energy from the reader can not support the hash function in reality, which hinders the widespread deployment of hash-enabled unknown tag identification protocols. To conquer this tough issue, we propose two approaches to efficiently identify unknown COTS RFID tags. We first propose a Single-Point Selective unknown tag identification approach called SPS, where an analog hash pattern using the EPC (Electronic Product Code) segments is deployed to exclusively identify unknown tags. An unknown tag will be identified when it selects a singleton slot to reply. To improve the time efficiency of SPS, we further propose a Multi-Point Selective unknown tag identification approach called MPS. In MPS, two techniques of batch identification and batch division are developed to reduce the number of empty slots and avoid tag collisions, respectively. Then the parameters are theoretically analyzed to maximize the identification efficiency. The effectiveness of the proposed approaches is validated via both the simulations and COTS RFID device based experiments.

Network motifs, as a fundamental higher-order structure in large-scale networks, have received significant attention over recent years. Particularly in heterogeneous networks, motifs offer a higher capacity to uncover diverse information compared to homogeneous networks. However, the structural complexity and heterogeneity pose challenges in coding, counting, and profiling heterogeneous motifs. This work addresses these challenges by first introducing a novel heterogeneous motif coding method, adaptable to homogeneous motifs as well. Building upon this coding framework, we then propose GIFT, a heterogeneous network motif counting algorithm. GIFT effectively leverages combined structures of heterogeneous motifs through three key procedures: neighborhood searching, motif combination, and redundant motif filtering. We apply GIFT to count three-order and four-order motifs across eight distinct heterogeneous networks. Subsequently, we profile these detected motifs using four classical motif-based indicators. Experimental results demonstrate that by appropriately selecting motifs tailored to specific networks, heterogeneous motifs emerge as significant features in characterizing the underlying network structure.

Network embedding aims to represent nodes with low dimensional vectors while preserving structural information. It has been recently shown that many popular network embedding methods can be transformed into matrix factorization problems. In this paper, we propose the unifying framework “Z-NetMF,” which generalizes random walk samplers to Z-Laplacian graph filters, leading to embedding algorithms with interpretable parameters. In particular, by controlling biases in the time domain, we propose the Z-NetMF-t algorithm, making it possible to scale contributions of random walks of different length. Inspired by node2vec, we design the Z-NetMF-g algorithm, capturing the random walk biases in the graph domain. Moreover, we evaluate the effect of the bias parameters based on node classification and link prediction tasks. The results show that our algorithms, especially the combined model Z-NetMF-gt with biases in both domains, outperform the state-of-art methods while providing interpretable insights at the same time. Finally, we discuss future directions of the Z-NetMF framework.

In recent years, wireless rechargeable sensor networks (WRSNs) have gained significant attention in the research community due to the current advancements in wireless power transfer technology. In mobile charger scheduling, previous works primarily emphasized the survival rate of sensor nodes. However, the primary task of a WRSN is to monitor targets in a given area. Therefore, the coverage of targets (CoT) maximization should be the primary objective of mobile charger scheduling. In this paper, we shift the focus to the CoT maximization on-demand charging scheduling problem, and formulate it as a multi-objective optimization problem, aiming to simultaneously enhance the average coverage and energy efficiency. We prove that the problem is NP-hard by reformulating it as a Multiple Travelling Salesman Problem with Deadline. We first propose the multiple chargers scheduling scheme for maximizing coverage of targets called MaxCov, which is designed to optimize the charging scheduling process and improve network performance in terms of coverage. Then, we further propose the multiple chargers scheduling scheme based on requests grouping called MaxCov-RG, which can well balance the trade-off between the performance and computational complexity. Finally, we validate the effectiveness of the proposed schemes via extensive simulations.

In the Dynamic Rechargeable Networks (DRNs), to maximize the throughput by efficient energy allocation, the existing studies usually consider the spatio-temporal dynamic factors of the harvested energy, and seldom the network dynamic factors simultaneously, such as the time variable network resources and wireless interference. To take the network dynamic factors together, this paper studies the quite challenging problem, the network throughput maximization in the DRNs. We introduce the Time-Expanded Graph (TEG) to describe the above dynamic factors in an obvious way and design the Single Pair Throughput maximization (SPT) algorithm based on TEG. In the case of multiple pairs of source-targets, this paper introduces the Garg and Könemann's framework and then designs the Multiple Pairs Throughput (MPT) algorithm to maximize the overall throughput of all pairs. To reduce the time complexity, this paper proposes a Distributed and Parallel Throughput algorithm (DPT). In real applications, the network dynamic factors may not be known in advance. This paper proposes an Online Time-Span Algorithm (OTA) with Markov approximation and Lyapunov optimization, and conducts the extensive numerical evaluation based on the simulated data and the data collected by our real system. The numerical simulation results demonstrate the throughput improvement of our algorithms.

In numerous network analysis tasks, feature representation plays an imperative role. Due to the intrinsic nature of networks being discrete, enormous challenges are imposed on their effective usage. There has been a significant amount of attention on network feature learning in recent times that has the potential of mapping discrete features into a continuous feature space. The methods, however, lack preserving the structural information owing to the utilization of random negative sampling during the training phase. The ability to effectively join attribute information to embedding feature space is also compromised. To address the shortcomings identified, a novel attribute force-based graph (AGForce) learning model is proposed that keeps the structural information intact along with adaptively joining attribute information to the node's features. To demonstrate the effectiveness of the proposed framework, comprehensive experiments on benchmark datasets are performed. AGForce based on the spring-electrical model extends opportunities to simulate node interaction for graph learning.

As one of the significant supporting technologies for mobile virtual reality (MVR), computer vision is latency-sensitive and always requires real-time response and accurate object analysis. However, the limited computational resources of mobile devices lead to high service delay and low analysis quality, resulting in poor quality of service (QoS). By placing the edge service entities (SEs) of the video tasks on the edge server close to the mobile users, a satisfactory QoS can be obtained for MVR systems. Most of the previous works are restricted to optimizing QoS through service placement, while ignoring the key impact of the network access point and video frame resolution selections on QoS. In this paper, we propose an edge service entity placement model, which aims to jointly optimize service delay and analysis quality for MVR systems. Specifically, we design an efficient dynamic edge service entity placement scheme (EDSP-Edge) based on the block coordinate descent theory, which dynamically determines the selection strategies of network access points, service entities and video frame resolutions for users to effectively improve the QoS. We theoretically analyze the performance of EDSP-Edge and get the gap between EDSP-Edge and the optimal performance. Finally, extensive real-data driven simulations are conducted to show that the EDSP-Edge performs close to the optimal scheme and achieves at least 22% performance improvement compared with previous works.

Graph Neural Networks (GNNs) are powerful tools for graph representation. However, GNNs have remained black boxes, leading to the lack of explainability. As a consequence, the application of GNNs has been severely limited. Existing methods focus on generating an explanation with important nodes and edges but pay less attention to high-order structures (e.g., network motif), which are more intuitive and important for graph data. The explanations generated by the explainer will thus ignore the high-order information contained in multi-node neighbours, resulting in a decrease in the human comprehensibility of the explanation subgraph. In this paper, we propose a motif-aware GNNs explainer (MEGA), wherein a motif-aware subgraph generation module and a counterfactual optimization layer are employed. MEGA can provide high-quality counterfactual explanations for GNNs while focusing on high-order features of graph data. We justify the effectiveness of the proposed MEGA on both synthetic and real-world datasets. Experimental results show that MEGA outperforms state-of-the-art baselines while keeping explanations at a smaller level.

As a novel learning paradigm, Federated learning (FL) aims at protecting privacy by avoiding raw data shifting between distributed clients and central servers. However, recent researches demonstrate the vulnerability of FL against gradient-based privacy attacks, in which, gradients intercepted by malicious adversaries may result in data leakage. Current defense methods suffer from performance drops, low privacy guarantees, and high communication costs. Motivated by this, we propose FedRSM, a Representational-Similarity-Based Secured Model Uploading for Federated Learning. FedRSM splits Deep Neural Networks (DNNs) into layers, calculates Representational Dissimilarity Vector (RDV), measures the similarity between local RDV and global RDV of each model layer, and constructs secured local model to be uploaded based on Representational Consistency Alteration (RCA). According to the evaluation result, FedRSM can improve testing accuracy by up to 2%, significantly reduce communication costs, and avoid data leakage under different model complexities.

Understanding student behavior patterns is fundamental to building smart campuses. However, the diversity of student behavior and the complexity of educational data not only bring great obstacles to the relevant research, but also leads to unstable performance and low reliability of current student behavior analysis systems. The emergence of educational big data and the latest advances in deep learning and representation learning provide unprecedented opportunities to tackle the above problems. In this talk, we introduce how we mine and analyze student behavior patterns by overcoming the complexity of educational data. Specifically, we propose a series of algorithmic frameworks, which take advantage of network science, data mining, and machine learning to form a data-driven system for mining and analyzing student behavior patterns. Our research not only fills the gap in the field of student abnormal behavior warning and student status monitoring, but also provides insights into data-driven smart city construction.

Academic conferences have been proven to be significant in facilitating academic activities. To promote information retrieval specific to academic conferences, building complete, systematic, and professional conference knowledge graphs is a crucial task. However, many related systems mainly focus on general knowledge of overall academic information or concentrate services on specific domains. Aiming at filling this gap, this work demonstrates a novel conference knowledge graph, namely Web of Conferences. The system accommodates detailed conference profiles, conference ranking lists, intelligent conference queries, and personalized conference recommendations. Web of Conferences supports detailed conference information retrieval while providing the ranking of conferences based on the most recent data. Conference queries in the system can be implemented via precise search or fuzzy search. Then, according to users' query conditions, personalized conference recommendations are available. Web of Conferences is demonstrated with a user-friendly visualization interface and can be served as a useful information retrieval system for researchers.

Recent years have witnessed significant advances in graph contrastive learning (GCL), while most GCL models use graph neural networks as encoders based on supervised learning. In this work, we propose a novel graph learning model called GraphTL, which explores self-supervised teaching and learning of representations on graphs. One critical objective of GCL is to retain original graph information. For this purpose, we design an encoder based on the idea of unsupervised dimensionality reduction of locally linear embedding (LLE). Specifically, we map one iteration of the LLE to one layer of the network. To guide the encoder to better retain the original graph information, we propose an unbalanced contrastive model consisting of two views, which are the learning view and the teaching view, respectively. Furthermore, we consider the nodes that are identical in muti-views as positive node pairs, and design the node similarity scorer so that the model can select positive samples of a target node. Extensive experiments have been conducted over multiple datasets to evaluate the performance of GraphTL in comparison with baseline models. Results demonstrate that GraphTL can reduce distances between similar nodes while preserving network topological and feature information, yielding better performance in node classification.

Graph convolutional neural network (GCN) is a powerful deep learning framework for network data. However, variants of graph neural architectures can lead to drastically different performance on different tasks. Model comparison calls for a unifying framework with interpretability and principled experimental procedures. Based on the theories from graph signal processing (GSP), we show that GCN’s capability is fundamentally limited by the uncertainty principle, and wavelets provide a controllable trade-off between local and global information. We adapt wavelet denoising filters to the graph domain, unifying popular variants of GCN under a common interpretable mathematical framework. Furthermore, we propose WaveThresh and WaveShrink which are novel GCN models based on proven denoising filters from the signal processing literature. Empirically, we evaluate our models and other popular GCNs under a more principled procedure and analyze how trade-offs between local and global graph signals can lead to better performance in different datasets.

Abstract The transition from secondary education to higher education could be challenging for most freshmen. For students who fail to adjust to university life smoothly, their status may worsen if the university cannot offer timely and proper guidance. Helping students adapt to university life is a long‐term goal for any academic institution. Therefore, understanding the nature of the maladaptation phenomenon and the early prediction of “at‐risk” students are crucial tasks that urgently need to be tackled effectively. This article aims to analyze the relevant factors that affect the maladaptation phenomenon and predict this phenomenon in advance. We develop a prediction framework (MAladaptive STudEnt pRediction, MASTER) for the early prediction of students with maladaptation. First, our framework uses the SMOTE (Synthetic Minority Oversampling Technique) algorithm to solve the data label imbalance issue. Moreover, a novel ensemble algorithm, priority forest, is proposed for outputting ranks instead of binary results, which enables us to perform proactive interventions in a prioritized manner where limited education resources are available. Experimental results on real‐world education datasets demonstrate that the MASTER framework outperforms other state‐of‐art methods.

With the rapid development of Artificial Intelligence (AI) and Internet of Things (IoTs), an increasing number of computation intensive or delay sensitive biomedical data processing and analysis tasks are produced in vehicles, bringing more and more challenges to the biometric monitoring of drivers. Edge computing is a new paradigm to solve these challenges by offloading tasks from the resource-limited vehicles to Edge Servers (ESs) in Road Side Units (RSUs). However, most of the traditional offloading schedules for vehicular networks concentrate on the edge, while some tasks may be too complex for ESs to process. To this end, we consider a collaborative vehicular network in which the cloud, edge and terminal can cooperate with each other to accomplish the tasks. The vehicles can offload the computation intensive tasks to the cloud to save the resource of edge. We further construct the virtual resource pool which can integrate the resource of multiple ESs since some regions may be covered by multiple RSUs. In this paper, we propose a Multi-Scenario offloading schedule for biomedical data processing and analysis in Cloud-Edge-Terminal collaborative vehicular networks called MSCET. The parameters of the proposed MSCET are optimized to maximize the system utility. We also conduct extensive simulations to evaluate the proposed MSCET and the results illustrate that MSCET outperforms other existing schedules.

Online dating is an increasingly thriving business which boosts billion-dollar revenues and attracts users in the tens of millions. Despite its popularity, internet dating is not exempt from the concerns about privacy and trust posed by the revelation of potentially sensitive data as well as the exposure to self-reported (and hence potentially distorted) information. The increasing popularity of online dating networks leads to an increase in security concerns and challenges, as well as harmful actions and attacks, such as creating fake accounts, phishing on these networks. To maintain the safety of legitimate online dating users, it is critical to recognize and isolate criminal people as soon as possible. However, researchers concerning malicious user detection in dating social networks are merely a few. To address some key challenges in this space, we propose a trust-aware detection framework to detect malicious users based on different kinds of data from a real dating site. In particular, we develop a user trust model to distinguish between malicious and legitimate users. Furthermore, we propose a novel data-balancing method to improve the recall rate of malicious user detection. Extensive experiments have been conducted over real-world datasets. The results show that the proposed approach yields a precision of up to 59.16% and a recall rate of up to 73%, which is significantly higher than other baseline algorithms.

COVID-19 has spread all over the world, accounting for countless death and enormous economic loss. Since the World Health Organization (WHO) declared COVID-19 as a pandemic, governments from different countries have made various policies to prevent the pandemic from becoming worse. However, civilian reactions to the pandemic vary when they face similar situations. This behavioral variation creates a challenge when it comes to policy-making. Such differences are generally implicit, hidden in ones’ social lives. As a result, it is challenging to analyze such differences when the governments make policies. In this work, we investigate social media posts on Twitter and Weibo in order to effectively explore the difference in reactions across various countries, with the aim to understand national differences. To this end, we employ natural language processing (NLP) methods and Linguistic Inquiry and Word Count (LIWC) tools to process six languages in different countries, including the USA, Germany, France, Italy, the U.K., and China. We provide a comprehensive analysis of public reaction differences from the emotional perspective. Our findings verify that the reactions vary noticeably among various countries for some policies. Therefore, sentiment analysis can significantly influence policy-making. Our work sheds light on the mechanism of detecting the reaction differences in various countries, which can be utilized to conduct effective communication and make appropriate policy decisions.

Facial perception is of significant influence on the positions of people in social networks. Particularly, students’ facial traits can affect their social centrality in educational settings (e.g., students looking intelligent can attract more friends). However, in educational environments, the social biases associated with appearances have alarming consequences, and little research has been done to investigate the effect of facial perception on social networks. Therefore, it is necessary to comprehensively analyze the influence of perceived facial traits on students’ status in social interaction. In this article, we explore the effect of facial perception on the social centrality of students in social networks. Because students’ social centrality is based on both their study ability and facial traits, this study does a comparative analysis of how facial perception and academic performance influence the social centrality of students. Subsequently, the experimental results demonstrate that facial perception, as well as academic performance, closely correlates with the social centrality of students. Finally, this study contributes to a comprehensive and deep understanding of social networks by analyzing facial trait-based social biases.

Anomaly analytics is a popular and vital task in various research contexts that has been studied for several decades. At the same time, deep learning has shown its capacity in solving many graph-based tasks, like node classification, link prediction, and graph classification. Recently, many studies are extending graph learning models for solving anomaly analytics problems, resulting in beneficial advances in graph-based anomaly analytics techniques. In this survey, we provide a comprehensive overview of graph learning methods for anomaly analytics tasks. We classify them into four categories based on their model architectures, namely graph convolutional network, graph attention network, graph autoencoder, and other graph learning models. The differences between these methods are also compared in a systematic manner. Furthermore, we outline several graph-based anomaly analytics applications across various domains in the real world. Finally, we discuss five potential future research directions in this rapidly growing field.

The COVID-19 pandemic has posed great challenges to public health services, government agencies, and policymakers, raising huge social conflicts between public health and economic resilience. Policies such as reopening or closure of business activities are formulated based on scientific projections of infection risks obtained from infection dynamics models. Though most parameters in epidemic prediction service models can be set with domain knowledge of COVID-19, a key parameter, namely, human mobility, is often challenging to estimate due to complex spatio-temporal correlations and social contexts under escalating COVID-19 facilities. Moreover, how to integrate the various implicit features to accurately predict infectious cases is still an open issue. To address this challenge, we formulate the problem as a spatio-temporal network representation problem and propose STEP, a Spatio-Temporal Epidemic Prediction framework, to estimate pandemic infection risk of a city by integrating various real-world conditions (e.g., City Risk Index, climate, and medical conditions) into graph-structured data. We also employ a multi-head attention mechanism in representation learning to extract implicit features for a given city. Extensive experiments have been conducted upon the real-world dataset for 51 states (50 states and Washington, D.C.) of the USA. Experimental results show that STEP can yield more accurate pandemic infection risk estimation than baseline methods. Moreover, STEP outperforms other methods in both short-term and long-term prediction.

Predicting traffic accidents can help traffic management departments respond to sudden traffic situations promptly, improve drivers’ vigilance, and reduce losses caused by traffic accidents. However, the causality of traffic accidents is complex and difficult to analyze. Most existing traffic accident prediction methods do not consider the dynamic spatio-temporal correlation of traffic data, which leads to unsatisfactory prediction accuracy. To address this issue, we propose a multi-task learning framework (TAP) based on the Spatio-temporal Variational Graph Auto-Encoders (ST-VGAE) for traffic accident profiling. We firstly capture the dynamic spatio-temporal correlation of traffic conditions through a spatio-temporal graph convolutional encoder and embed it as a low-latitude vector. Then, we use a multi-task learning scheme to combine external factors to generate the traffic accident profiling. Furthermore, we propose a traffic accident profiling application framework based on edge computing. This method increases the speed of calculation by offloading the calculation of traffic accident profiling to edge nodes. Finally, the experimental results on real datasets demonstrate that TAP outperforms other state-of-the-art baselines.

Data explosion in the information society drives people to develop more effective ways to extract meaningful information. Extracting semantic information and relational information has emerged as a key mining primitive in a wide variety of practical applications. Existing research on relation mining has primarily focused on explicit connections and ignored underlying information, e.g., the latent entity relations. Exploring such information (defined as implicit relationships in this article) provides an opportunity to reveal connotative knowledge and potential rules. In this article, we propose a novel research topic, i.e., how to identify implicit relationships across heterogeneous networks. Specially, we first give a clear and generic definition of implicit relationships. Then, we formalize the problem and propose an efficient solution, namely MIRROR, a graph convolutional network (GCN) model to infer implicit ties under explicit connections. MIRROR captures rich information in learning node-level representations by incorporating attributes from heterogeneous neighbors. Furthermore, MIRROR is tolerant of missing node attribute information because it is able to utilize network structure. We empirically evaluate MIRROR on four different genres of networks, achieving state-of-the-art performance for target relations mining. The underlying information revealed by MIRROR contributes to enriching existing knowledge and leading to novel domain insights.

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field.

Graph Convolutional Networks (GCNs) have achieved impressive performance in a wide variety of areas, attracting considerable attention. The core step of GCNs is the information-passing framework that considers all information from neighbors to the central vertex to be equally important. Such equal importance, however, is inadequate for scale-free networks, where hub vertices propagate more dominant information due to vertex imbalance. In this paper, we propose a novel centrality-based framework named CenGCN to address the inequality of information. This framework first quantifies the similarity between hub vertices and their neighbors by label propagation with hub vertices. Based on this similarity and centrality indices, the framework transforms the graph by increasing or decreasing the weights of edges connecting hub vertices and adding self-connections to vertices. In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices. We present two variants CenGCN_D and CenGCN_E, based on degree centrality and eigenvector centrality, respectively. We also conduct comprehensive experiments, including vertex classification, link prediction, vertex clustering, and network visualization. The results demonstrate that the two variants significantly outperform state-of-the-art baselines.

Outlier detection is an important data mining task, and developing effective methods to detect outliers is challenging in cases where there is insufficient labeled data. Manually labeling the data is labor-intensive and time-consuming. Because of a limited number of labeled samples, the classes are unbalanced, resulting in a class-imbalance problem. Existing methods fail to address these aforementioned issues holistically and fall short in generating quality outlier samples for effective outlier detection accuracy. In this paper, we propose a new solution that tackles these problems. We propose a. Generative Adversarial Active Learning method (DIR-GAAL), which generates Diverse, Informative, and Representative outlier samples through active learning, and employs the mini-max game between the generator and discriminator in a generative adversarial network. We conducted extensive experiments on several benchmark datasets to evaluate the performance of our method. When compared to other benchmark methods, our method consistently demon-strates better outlier detection accuracy without being negatively affected by the class-imbalance problem.

Citation data, along with other bibliographic datasets, have long been adopted by the knowledge and data discovery community as an important direction for presenting the validity and effectiveness of proposed algorithms and strategies. Many top computer scientists are also excellent researchers in the science of science. The purpose of this workshop is to bridge the two communities (i.e., the knowledge discovery community and the science of science community) together as the scholarly activities become salient web and social activities that start to generate a ripple effect on broader knowledge discovery communities. This workshop will showcase the current data-driven science of science research by highlighting several studies and constructing a community of researchers to explore questions critical to the future of data-driven science of science, especially a community of data-driven science of science in Data Science so as to facilitate collaboration and inspire innovation. Through discussion on emerging and critical topics in the science of science, this workshop aims to help generate effective solutions for addressing environmental, societal, and technological problems in the scientific community.

Memes have become the popular means of communication for Internet users worldwide. Understanding the Internet meme is one of the most tricky challenges in natural language processing (NLP) tasks due to its convenient non-standard writing and network vocabulary. Recently, many linguists suggested that memes contain rich metaphorical information. However, the existing researches ignore this key feature. Therefore, to incorporate informative metaphors into the meme analysis, we introduce a novel multimodal meme dataset called MET-Meme, which is rich in metaphorical features. It contains 10045 text-image pairs, with manual annotations of the metaphor occurrence, sentiment categories, intentions, and offensiveness degree. Moreover, we propose a range of strong baselines to demonstrate the importance of combining metaphorical features for meme sentiment analysis and semantic understanding tasks, respectively. MET-Meme, and its code are released publicly for research in \urlhttps://github.com/liaolianfoka/MET-Meme-A-Multi-modal-Meme-Dataset-Rich-in-Metaphors.

In this era of the Internet of Everything (IoE), edge computing has emerged as the critical enabling technology to solve a series of issues caused by an increasing amount of interconnected devices and large-scale data transmission. However, the deficiencies of edge computing paradigm are gradually being magnified in the context of IoE, especially in terms of service migration, security and privacy preservation, and deployment issues of edge node. These issues can not be well addressed by conventional approaches. Thanks to the rapid development of upcoming technologies, such as artificial intelligence (AI), blockchain, and microservices, novel and more effective solutions have emerged and been applied to solve existing challenges. In addition, edge computing can be deeply integrated with technologies in other domains (e.g., AI, blockchain, 6G, and digital twin) through interdisciplinary intersection and practice, releasing the potential for mutual benefit. These promising integrations need to be further explored and researched. In addition, edge computing provides strong support in applications scenarios, such as remote working, new physical retail industries, and digital advertising, which has greatly changed the way we live, work, and study. In this article, we present an up-to-date survey of the edge computing research. In addition to introducing the definition, model, and characteristics of edge computing, we discuss a set of key issues in edge computing and novel solutions supported by emerging technologies in IoE era. Furthermore, we explore the potential and promising trends from the perspective of technology integration. Finally, new application scenarios and the final form of edge computing are discussed.

Citation recommendation plays an important role in the context of scholarly big data, where finding relevant papers has become more difficult because of information overload. Applying traditional collaborative filtering (CF) to citation recommendation is challenging due to the cold start problem and the lack of paper ratings. To address these challenges, in this article, we propose a collaborative filtering with network representation learning framework for citation recommendation, namely CNCRec, which is a hybrid user-based CF considering both paper content and network topology. It aims at recommending citations in heterogeneous academic information networks. CNCRec creates the paper rating matrix based on attributed citation network representation learning, where the attributes are topics extracted from the paper text information. Meanwhile, the learned representations of attributed collaboration network is utilized to improve the selection of nearest neighbors. By harnessing the power of network representation learning, CNCRec is able to make full use of the whole citation network topology compared with previous context-aware network-based models. Extensive experiments on both DBLP and APS datasets show that the proposed method outperforms state-of-the-art methods in terms of precision, recall, and MRR (Mean Reciprocal Rank). Moreover, CNCRec can better solve the data sparsity problem compared with other CF-based baselines.

Region profiles are summaries of characteristics of urban regions. Region profiling is a process to discover the correlations between urban regions. The learned urban profiles can be used to represent and identify regions in supporting downstream tasks, e.g., region traffic status estimation. While some efforts have been made to model urban regions, representation learning with awareness of graph-structured data can improve the existing methods. To do this, we first construct an attribute spatio-temporal graph, in which a node represents a region, an edge represents mobility across regions, and a node attribute represents a region’s point of interest (PoI) distribution. The problem of region profiling is reformulated as a representation learning problem based on attribute spatio-temporal graphs. To solve this problem, we developed URGENT, a spatio-temporal graph learning framework. URGENT is made up of two modules. The graph convolutional neural network is used in the first module to learn spatial dependencies. The second module is an encoding–decoding temporal learning structure with self-attention mechanism. Furthermore, we use the learned representations of regions to estimate region traffic status. Experimental results demonstrate that URGENT outperforms major baselines in estimation accuracy under various settings and produces more meaningful results.

Collaborative teamwork is key to major scientific discoveries. However, the prevalence of collaboration among researchers makes team recognition increasingly challenging. Previous studies have demonstrated that people are more likely to collaborate with individuals they are familiar with. In this work, we employ the definition of familiarity and then propose faMiliarity-based cOllaborative Team recOgnition (MOTO) algorithm to recognize collaborative teams. MOTO calculates the shortest distance matrix within the global collaboration network and the local density of each node. Central team members are initially recognized based on local density. Then, MOTO recognizes the remaining team members by using the familiarity metric and shortest distance matrix. Extensive experiments have been conducted upon a large-scale dataset. The experimental results show that compared with baseline methods, MOTO can recognize the largest number of teams. The teams recognized by the MOTO possess more cohesive team structures and lower team communication costs compared with other methods. MOTO utilizes familiarity in team recognition to identify cohesive academic teams. The recognized teams are in line with real-world collaborative teamwork patterns. Based on team recognition using MOTO, the research team structure and performance are further analyzed for given time periods. The number of teams that consist of members from different institutions increases gradually. Such teams are found to perform better in comparison with those whose members are from the same institution.

N OWADAYS, billions of devices are connected to the In-ternet, enabling Internet of Things (IoT) systems widely deployed, such as smart city, smart healthcare and intelligent plant, to capture a great quantity of sensing data. Consequently, the data transmission, processing and analysis in IoT applications bring a great pressure to the central server. Fortunately, distributed intelligence becomes one of the potential solutions. Distributed intelligence can greatly relieve server pressures via plenty of terminal devices, and these devices collaboratively perceive and handle the mass data to improve the reliability, s-calability and security of industrial IoT systems. As future IoT system will embrace more wireless sensors and devices, the high-performance computing, high-bandwidth and low-latency communication are excessively required, many new research opportunities and challenges for distributed intelligence over Internet of things have arisen. To promote the development of distributed intelligence technology, this special section (SS) focuses on various technologies and platforms regarding industrial IoT systems. This special section received nearly 50 submitted manuscripts, out of which 10 of them have been accepted after a rigorous peer review. Each manuscript is reviewed by multiple rounds of review with at least three or four reviewers, the problems to be solved and the innovation of each manuscript are mainly concerned. Then the accepted papers are summarized as follows in details. Considering the joint optimization of the offloading decision and resource allocation under limited resource constraints in collaborative edge computing networks with multiple IIoT devices and MEC servers, an improved differential evolution algorithm [7] is proposed to minimize the weighted sum of cost of energy consumption and time delay, which can effectively reduce the system delay and energy consumption. In order to improve the performance of task scheduling in cloud computing, Attiya et al. [1] propose a novel hybrid swarm intelligence method MRFOSSA, which uses a modified Manta-Ray Foraging Optimizer (MRFO) and the Salp Swarm Algorithm (SSA). MRFOSSA is superior to other methods in terms of makespan time and cloud throughput. The research goal of the paper [5] is to design an intelligent computing offloading strategy for industrial applications in order to optimize costs and mitigate energy losses. Then the paper proposes to combine a fog controller and AI-based learning techniques so that the fog controller can intelligently assign tasks to the most appropriate fog devices and find the appropriate path to the target. Considering the resource utilization efficiency under dynamic overload requests and network states in IIoT, Chen et al. [2] propose DRL-based intelligent SFC orchestration scheme and jointly optimize the VNF deployment and SFC embedment by the improved DDQN algorithm, which can improve the performance of resource utilization rate, execution cost and delay compared with other representative schemes. To solve the problem of resource allocation and energy cost in Internet of Vehicles, Kong et al. [8] design a joint computing and caching framework and formulate the problem as a reinforcement learning problem to minimize the energy cost. On this basis, the optimization algorithm based on DDPG is proposed, which can effectively decrease energy costs. To reduce the query numbers of the object model when constructing adversarial examples, Zhang et al. [10] propose generating adversarial examples with shadow model (GASM), i.e., transfering the query operations to the designed shadow model, which can achieve high attack success rates. Chen et al. [3] revise a Decentralized-Wireless-Federated-Learning algorithm (DWFL) which utilizes the superposition property of the analog scheme. It can solve the problem of single failure, limited bandwidth resource and privacy protection in wireless federated learning algorithm, which can be applied widely in wireless IoT networks. To reduce the resource consumption in CNN-based applications, Jia et al. [6] propose the CNN-based Resource Optimization APProach which utilizes model compression and computation sharing to optimize inner-model and inter-model respectively, and the comparison results show the superior performance in scalability and the decrease of resource cost. In mobile crowdsensing activities, Gao et al. [4] propose a differential Location Privacy-preserving Mechanism based on Trajectory obfuscation (LPMT) to protect the location privacy of mobile users, which includes three operations: stay points extraction, stay points obfuscation and stay points sampling. In order to mimic the task-free bottom-up visual attention process by predicting salient regions on natural images, Umer et al. [9] propose a Pseudo Knowledge Distillation (PKD) model based on knowledge distillation and pseudo labelling technique, which is computationally efficient and suitable for real-time on-device saliency prediction.

Traffic flow prediction is an integral part of an intelligent transportation system and thus fundamental for various traffic-related applications. Buses are an indispensable way of moving for urban residents with fixed routes and schedules, which leads to latent travel regularity. However, human mobility patterns, specifically the complex relationships between bus passengers, are deeply hidden in this fixed mobility mode. Although many models exist to predict traffic flow, human mobility patterns have not been well explored in this regard. To address this research gap and learn human mobility knowledge from this fixed travel behaviors, we propose a multi-pattern passenger flow prediction framework, MPGCN, based on Graph Convolutional Network (GCN). Firstly, we construct a novel sharing-stop network to model relationships between passengers based on bus record data. Then, we employ GCN to extract features from the graph by learning useful topology information and introduce a deep clustering method to recognize mobility patterns hidden in bus passengers. Furthermore, to fully utilize spatio-temporal information, we propose GCN2Flow to predict passenger flow based on various mobility patterns. To the best of our knowledge, this paper is the first work to adopt a multi-pattern approach to predict the bus passenger flow by taking advantage of graph learning. We design a case study for optimizing routes. Extensive experiments upon a real-world bus dataset demonstrate that MPGCN has potential efficacy in passenger flow prediction and route optimization.

Anomaly detection is one of the most active research areas in various critical domains, such as healthcare, fintech, and public security. However, little attention has been paid to scholarly data, that is, anomaly detection in a citation network. Citation is considered as one of the most crucial metrics to evaluate the impact of scientific research, which may be gamed in multiple ways. Therefore, anomaly detection in citation networks is of significant importance to identify manipulation and inflation of citations. To address this open issue, we propose a novel deep graph learning model, namely graph learning for anomaly detection (GLAD), to identify anomalies in citation networks. GLAD incorporates text semantic mining to network representation learning by adding both node attributes and link attributes via graph neural networks (GNNs). It exploits not only the relevance of citation contents, but also hidden relationships between papers. Within the GLAD framework, we propose an algorithm called Citation PUrpose (CPU) to discover the purpose of citation based on citation context. The performance of GLAD is validated through a simulated anomalous citation dataset. Experimental results demonstrate the effectiveness of GLAD on the anomalous citation detection task.

Anomaly detection (such as telecom fraud detection and medical image detection) has attracted the increasing attention of people. The complex interaction between multiple entities widely exists in the network, which can reflect specific human behavior patterns. Such patterns can be modeled by higher-order network structures, thus benefiting anomaly detection on attributed networks. However, due to the lack of an effective mechanism in most existing graph learning methods, these complex interaction patterns fail to be applied in detecting anomalies, hindering the progress of anomaly detection to some extent. In order to address the aforementioned issue, we present a higher-order structure based anomaly detection (GUIDE) method. We exploit attribute autoencoder and structure autoencoder to reconstruct node attributes and higher-order structures, respectively. Moreover, we design a graph attention layer to evaluate the significance of neighbors to nodes through their higher-order structure differences. Finally, we leverage node attribute and higher-order structure reconstruction errors to find anomalies. Extensive experiments on five real-world datasets (i.e., ACM, Citation, Cora, DBLP, and Pubmed) are implemented to verify the effectiveness of GUIDE. Experimental results in terms of ROC-AUC, PR-AUC, and Recall@K show that GUIDE significantly outperforms the state-of-art methods.

Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students’ mental issues.

Generalized zero-shot learning (GZSL) has attracted considerable attention recently, which trains models with data from seen classes and tests on data from both seen and unseen classes. Most of the existing methods attempt to find a mapping from visual space to semantic space, such mapping can easily result in the domain shift problem. To address this issue, we propose a Multiple-Input Multiple-Output Fusion Network to GZSL. It can generate similar common semantic representation to paired inputs even with only the class semantic embeddings. This makes it possible to synthesize pseudo samples from attributes of unseen classes. Extensive experiments carried out on three benchmark datasets show the effectiveness of the proposed model.

Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor.

In the Dynamic Rechargeable Networks (DRNs), the existing studies usually consider the spatio-temporal dynamics of the harvested energy so as to maximize the throughput by efficient energy allocation. However, the network dynamics have seldom been considered simultaneously including the time variable link quality, communication power and battery charge efficiency. Furthermore, the wireless interference brings extra challenge. To take these dynamics into account together, this paper studies the quite challenging problem, the network throughput maximization in the DRNs, by proper energy allocation while considering the additional affection of wireless interference. We introduce the Time-Expanded Graph (TEG) to describe the above dynamics in a feasible easy way, and then look into the scenario where there is only one pair of source-target firstly. To maximize the throughput, this paper designs the Single Pair Throughput maximization (SPT) algorithm based on TEG while considering the wireless interference. In the case of multiple pairs of source-targets, it’s quite complex to solve the network throughput maximization problem directly. This paper introduces the Garg and Könemanns framework and then designs the Multiple Pairs Throughput (MPT) algorithm to maximize the overall throughput of all pairs. MPT is a fast approximation solution with the ratio of 1-3ϵ, where 0 < ϵ < 1 is a small positive constant. This paper also conducts the extensive numerical evaluation based on the simulated data and the data collected by our real system. The numerical simulation results demonstrate the throughput improvement of our algorithms.

Natural language processing technologies, such as topic models, have been proven to be effective for scholarly recommendation tasks with the ability to deal with content information. Recently, venue recommendation is becoming an increasingly important research task due to the unprecedented number of publication venues. However, traditional methods focus on either the author’s local network or author-venue similarity, where the multiple relationships between scholars and venues are overlooked, especially the venue–venue interaction. To solve this problem, we propose an author topic model–enhanced joint graph modeling approach that consists of venue topic modeling, venue-specific topic influence modeling, and scholar preference modeling. We first model the venue topic with Latent Dirichlet Allocation. Then, we model the venue-specific topic influence in an asymmetric and low-dimensional way by considering the topic similarity between venues, the top-influence of venues, and the top-susceptibility of venues. The top-influence characterizes venues’ capacity of exerting topic influence on other venues. The top-susceptibility captures venues’ propensity of being topically influenced by other venues. Extensive experiments on two real-world datasets show that our proposed joint graph modeling approach outperforms the state-of-the-art methods.

Scientific collaboration has become a universal phenomenon in recent years. Meanwhile, scholars tend to hunt for surprising collaborators for broadening their horizons. Serendipity initially denotes the fortunate discovery. Although a lot of literature is available on the topic of serendipity, little research has investigated serendipity in scientific collaborations. The objective of this paper is to identify serendipitous scientific collaborators of target scholars based on their collaboration data. First, we induce the definition of serendipitous scientific collaborators by three components, which are relevance, unexpectedness, and value, respectively. They are quantified as three intuitive indices corresponding to the network proximity, topic diversity, and collaborator influence, respectively. Second, we propose a classification model, called RUVMod, to classify all collaborators based on the analysis of three indices in definition. The serendipitous collaborator has lower network proximity, higher topic diversity and higher influence than his/her target scholar relatively. Finally, we cluster all collaborators via Self Organizing Maps and identify the serendipitous collaborator class according to the classes divided in our RUVMod. We apply our definition to the scientific collaborators extracted from DBLP dataset. The evaluation from the serendipity-based metrics suggests that RUVMod is effective in identifying serendipitous scientific collaborators.

COVID-19 has spread all over the world, having an enormous effect on our daily life and work. In response to the epidemic, a lot of important decisions need to be taken to save communities and economies worldwide. Data clearly play a vital role in effective decision-making. Data-driven decision-making uses data-related evidence and insights to guide the decision-making process and verify the plan of action before it is committed. To better handle the epidemic, governments and policy-making institutes have investigated abundant data originating from COVID-19. These data include those related to medicine, knowledge, media, and so on. Based on these data, many prevention and control policies are made. In this survey article, we summarize the progress of data-driven decision-making in the response to COVID-19, including COVID-19 prevention and control, psychological counseling, financial aid, work resumption, and school reopening. We also propose some current challenges and open issues in data-driven decision-making, including data collection and quality, complex data analysis, and fairness in decision-making. This survey article sheds light on current policy-making driven by data, which also provides a feasible direction for further scientific research.

In the age of social computing, finding interesting network patterns or motifs is significant and critical for various areas, such as decision intelligence, intrusion detection, medical diagnosis, social network analysis, fake news identification, and national security. However, subgraph matching remains a computationally challenging problem, let alone identifying special motifs among them. This is especially the case in large heterogeneous real-world networks. In this article, we propose an efficient solution for discovering and ranking human behavior patterns based on network motifs by exploring a user's query in an intelligent way. Our method takes advantage of the semantics provided by a user's query, which in turn provides the mathematical constraint that is crucial for faster detection. We propose an approach to generate query conditions based on the user's query. In particular, we use meta paths between the nodes to define target patterns as well as their similarities, leading to efficient motif discovery and ranking at the same time. The proposed method is examined in a real-world academic network using different similarity measures between the nodes. The experiment result demonstrates that our method can identify interesting motifs and is robust to the choice of similarity measures.

License plate is an essential characteristic to identify vehicles for the traffic management, and thus, license plate recognition is important for Internet of Vehicles. Since 5G has been widely covered, mobile devices are utilized to assist the traffic management, which is a significant part of Industry 4.0. However, there have always been privacy risks due to centralized training of models. Also, the trained model cannot be directly deployed on the mobile device due to its large number of parameters. In this article, we propose a federated learning-based license plate recognition framework (FedLPR) to solve these problems. We design detection and recognition model to apply in the mobile device. In terms of user privacy, data in individuals is harnessed on their mobile devices instead of the server to train models based on federated learning. Extensive experiments demonstrate that FedLPR has high accuracy and acceptable communication cost while preserving user privacy.

Industrial advancement has introduced a significant impact on ecological balance and natural resources; thus, pollution monitoring using smart sensors in the industrial Internet of Things (IIoT) has recently attracted growing interests in the era of Industry 4.0. However, the effective detection and location of polluted areas remains a major challenge for collecting and processing a massive amount of sensor data in the IIoT especially in far sea, danger zone, and mountain zone, where there is no communication infrastructure. In this article, we establish a satellite-terrestrial framework to detect and locate industrial pollution areas by integrating the satellite with the IIoT, and the massive amount of sensor data can be delivered to the satellite via a ground base station. Local attribute detection inspired by recent advances in graph signal processing provides a promising way for solving this problem. A subgraph can be formed by grouping the vertices with identical attributes, and these vertices can be easily separated from other vertices based on local attribute detection. In this article, new methods based on local attribute detection are proposed to detect and locate pollution areas. First, a stable wavelet statistic (SWS) is proposed by modeling the classical wavelet basis as a graph-based wavelet basis. To improve the generalization ability of the SWS, a new cluster center discovery method is proposed to minimize the distance between any vertex and the remaining vertices of the same cluster. Second, a smooth scan statistic is proposed by introducing a new constraint to simplify the problem formulation of the likelihood ratio test. The effectiveness of the two graph-based statistical methods is evaluated using real datasets for detecting and locating industrial pollution.

With the widely used Internet of Things, 5G, and smart city technologies, we are able to acquire a variety of vehicle trajectory data. These trajectory data are of great significance which can be used to extract relevant information in order to, for instance, calculate the optimal path from one position to another, detect abnormal behavior, monitor the traffic flow in a city, and predict the next position of an object. One of the key technology is to cluster vehicle trajectory. However, existing methods mainly rely on manually designed metrics which may lead to biased results. Meanwhile, the large scale of vehicle trajectory data has become a challenge because calculating these manually designed metrics will cost more time and space. To address these challenges, we propose to employ network representation learning to achieve accurate vehicle trajectory clustering. Specifically, we first construct the k-nearest neighbor-based internet of vehicles in a dynamic manner. Then we learn the low-dimensional representations of vehicles by performing dynamic network representation learning on the constructed network. Finally, using the learned vehicle vectors, vehicle trajectories are clustered with machine learning methods. Experimental results on the real-word dataset show that our method achieves the best performance compared against baseline methods.

While scientific collaboration is critical for a scholar, some collaborators can be more significant than others, e.g., lifetime collaborators. It has been shown that lifetime collaborators are more influential on a scholar’s academic performance. However, little research has been done on investigating predicting such special relationships in academic networks. To this end, we propose Scholar2vec, a novel neural network embedding for representing scholar profiles. First, our approach creates scholars’ research interest vector from textual information, such as demographics, research, and influence. After bridging research interests with a collaboration network, vector representations of scholars can be gained with graph learning. Meanwhile, since scholars are occupied with various attributes, we propose to incorporate four types of scholar attributes for learning scholar vectors. Finally, the early-stage similarity sequence based on Scholar2vec is used to predict lifetime collaborators with machine learning methods. Extensive experiments on two real-world datasets show that Scholar2vec outperforms state-of-the-art methods in lifetime collaborator prediction. Our work presents a new way to measure the similarity between two scholars by vector representation, which tackles the knowledge between network embedding and academic relationship mining.

The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines. This work aims to discover advisor-advisee relationships hidden behind scientific collaboration networks. For this purpose, we propose a novel model based on Network Representation Learning (NRL), namely Shifu2, which takes the collaboration network as input and the identified advisor-advisee relationship as output. In contrast to existing NRL models, Shifu2 considers not only the network structure but also the semantic information of nodes and edges. Shifu2 encodes nodes and edges into low-dimensional vectors respectively, both of which are then utilized to identify advisor-advisee relationships. Experimental results illustrate improved stability and effectiveness of the proposed model over state-of-the-art methods. In addition, we generate a large-scale academic genealogy dataset by taking advantage of Shifu2.

Finding both efficient and effective quantitative representations for scholars in scientific digital libraries has been a focal point of research. The unprecedented amounts of scholarly datasets, combined with contemporary machine learning and big data techniques, have enabled intelligent and automatic profiling of scholars from this vast and ever-increasing pool of scholarly data. Meanwhile, recent advance in network embedding techniques enables us to mitigate the challenges of large scale and sparsity of academic collaboration networks. In real-world academic social networks, scholars are accompanied with various attributes or features, such as co-authorship and publication records, which result in attributed collaboration networks. It has been observed that both network topology and scholar attributes are important in academic relationship mining. However, previous studies mainly focus on network topology, whereas scholar attributes are overlooked. Moreover, the influence of different scholar attributes are unclear. To bridge this gap, in this work, we present a novel framework of Attributed Collaboration Network Embedding (ACNE) for academic relationship mining. ACNE extracts four types of scholar attributes based on the proposed scholar profiling model, including demographics, research, influence, and sociability. ACNE can learn a low-dimensional representation of scholars considering both scholar attributes and network topology simultaneously. We demonstrate the effectiveness and potentials of ACNE in academic relationship mining by performing collaborator recommendation on two real-world datasets and the contribution and importance of each scholar attribute on scientific collaborator recommendation is investigated. Our work may shed light on academic relationship mining by taking advantage of attributed collaboration network embedding.

The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students' employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework.

Features representation leverages the great power in network analysis tasks. However, most features are discrete which poses tremendous challenges to effective use. Recently, increasing attention has been paid on network feature learning, which could map discrete features to continued space. Unfortunately, current studies fail to fully preserve the structural information in the feature space due to random negative sampling strategy during training. To tackle this problem, we study the problem of feature learning and novelty propose a force-based graph learning model named GForce inspired by the spring-electrical model. GForce assumes that nodes are in attractive forces and repulsive forces, thus leading to the same representation with the original structural information in feature learning. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed framework. Furthermore, GForce opens up opportunities to use physics models to model node interaction for graph learning.

Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results. We apply the acceleration procedure from the dimensional of network motifs. Specifically, the refined degree for nodes and edges are conducted in two stages: (1) employ motif degree of nodes to refine the adjacency matrix of the network; and (2) employ motif degree of edges to refine the transition probability matrix in the learning process. In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined. By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the original algorithms with higher efficiency.

Hashing technique has been widely applied to large-scale image retrieval due to its efficacy in storage and retrieval. However, due to the explosive growth of multimedia data on the web, existing hashing approaches can hardly achieve satisfactory performance on the newly-emerging images of new classes. In this paper, we propose a novel Semantic Augmentation Hashing (SAH) for zero-shot image retrieval. The class semantic embeddings are used as an intermediate space between visual features and binary codes to align visual features to corresponding class semantics and to transfer knowledge from seen classes to unseen classes simultaneously. Extensive experiments conducted on two datasets with different scales demonstrate the superiority of our method as compared against the state-of-the-arts.

In this work, we demonstrate a novel system, namely Web of Scholars, which integrates state-of-the-art mining techniques to search, mine, and visualize complex networks behind scholars in the field of Computer Science. Relying on the knowledge graph, it provides services for fast, accurate, and intelligent semantic querying as well as powerful recommendations. In addition, in order to realize information sharing, it provides open API to be served as the underlying architecture for advanced functions. Web of Scholars takes advantage of knowledge graph, which means that it will be able to access more knowledge if more search exist. It can be served as a useful and interoperable tool for scholars to conduct in-depth analysis within Science of Science.

This paper addresses the issues of selfishness, limited network resources, and their adverse effects on real-time dissemination of Emergency Warning Messages (EWMs) in modern Autonomous Moving Platforms (AMPs) such as Vehicular Social Networks (VSNs). For this purpose, we propose a social intelligence based identification mechanism to differentiate between a selfish and a cooperative node in the network. Therefore, we devise a crowdsensing based mechanism to calculate a tie-strength value based on several social metrics. Moreover, we design a recursive evolutionary algorithm for each node’s reputation calculation and update. Given that, then we estimate each node’s state-transition probability to select a super-spreader for rapid dissemination. In order to ensure a seamless and reliable dissemination process, we incorporate 5G network structure instead of conventional short range communication which is used in most vehicular networks at present. Finally, we design a real-time dissemination algorithm for EWMs and evaluate its performance in terms of network parameters such as delivery-ratio, delay, hop-count, and message-overhead for varying values of vehicular density, speed, and selfish nodes’ density based on realistic vehicular mobility traces. In addition, we present a comparative analysis of the performance of the proposed scheme with state-of-the-art dissemination schemes in VSNs.

Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this article, we propose a novel embedding algorithm that incorporates network motifs to capture higher order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the state-of-the-art embedding-based algorithms (by 19%).

Mobile crowdsourcing (MCS), as an effective and crucial technique of Industrial Internet of Things, is enabling smart city initiatives in the real world. It aims at incorporating the intelligence of dynamic crowds to collect and compute decentralized ubiquitous sensing data that can be used to solve major urbanization problems such as traffic congestion. The shared bus, as a neotype transportation mode, aims at improving the resource utilization rate and maintaining the advantages of convenience and economy. In this article, we provide a scheme to profile shared buses through heterogeneous mobile crowdsourced data (TRProfiling). First, we design an MCS-based shared bus data generation and collection solution to overcome the aforementioned data scarcity issue. Then, we propose a travel profiling to profile resident travel and design a method called multiconstraint evolution algorithm to optimize the routes. Experimental results demonstrate that TRProfiling has an excellent performance in satisfying passengers’ travel requirements.

Complex networks have become an active interdisciplinary field of research inspired by the empirical study of various networks. A subway network is a real-world example of complex networks in the transportation domain, which has attracted growing attention in network analysis recently. Analyzing human mobility patterns, specifically in ranking subway stations closely bounded by urban subway planning and individuals' travel experience, is still an open issue. In this paper, we propose a novel ranking method of station importance (SIRank) by utilizing human mobility patterns and improved PageRank algorithm. Specifically, by analyzing human mobility patterns of the subway system in Shanghai, we demonstrate both static and dynamic characteristics using two network models (Shanghai subway static network and Shanghai subway passenger network). In particular, the SIRank focuses on bi-directional passenger flow analysis between origins and destinations to iteratively generate the importance value for each station. We implement a range of the experiments to illustrate the effectiveness of SIRank using the real-world subway transaction datasets. The results demonstrate that the hit ratio in SIRank reaches 60% in the top five stations, which is much higher than that of ranking by a weighted mixed index (WMIRank) and ranking by node degree (NDRank) approaches.

This article elaborates how to identify and evaluate causal factors to improve scientific impact. Currently, analyzing scientific impact can be beneficial to various academic activities including funding application, mentor recommendation, discovering potential cooperators, and the like. It is universally acknowledged that high-impact scholars often have more opportunities to receive awards as an encouragement for their hard work. Therefore, scholars spend great efforts in making scientific achievements and improving scientific impact during their academic life. However, what are the determinate factors that control scholars’ academic success? The answer to this question can help scholars conduct their research more efficiently. Under this consideration, our article presents and analyzes the causal factors that are crucial for scholars’ academic success. We first propose five major factors including article-centered factors, author-centered factors, venue-centered factors, institution-centered factors, and temporal factors. Then, we apply recent advanced machine learning algorithms and jackknife method to assess the importance of each causal factor. Our empirical results show that author-centered and article-centered factors have the highest relevancy to scholars’ future success in the computer science area. Additionally, we discover an interesting phenomenon that the h -index of scholars within the same institution or university are actually very close to each other.

With the rapid industrialization and urbanization, pattern mining of soil contamination of heavy metals is attracting increasing attention to control soil contamination. However, the correlation over various heavy metals and the high-dimension representation of heavy metal data pose vast challenges on the accurate mining of patterns over heavy metals of soil contamination. To solve those challenges, a multiview Gaussian mixture model is proposed in this paper, to naturally capture complicated relationships over multiviews on the basis of deep fusion features of data. Specifically, a deep fusion feature architecture containing modality-specific and modality-common stacked autoencoders is designed to distill fusion representations from the information of all views. Then, the Gaussian mixture model is extended on the fusion representations to naturally recognize the accurate patterns of the intra- and inter-views. Finally, extensive experiments are conducted on the representative datasets to evaluate the performance of the multiview Gaussian mixture model. Results show the outperformance of the proposed methods.

In order to save time and cost, many disease gene prediction methods have been proposed in recent years. However, the traditional network model uses a binary relationship to represent the relationship between different proteins or gene molecules and phenotypes, which leads to the loss of information. Recently, hypergraph shows that it can overcome this loss of information to some extent and preserve the multivariate relationship, so we transformed the disease gene prediction problem into the problem of ranking the multivariate-relationship object. In this paper, we propose a method of Heterogeneous Probabilistic Hypergraph Ranking (HPHR) to predict disease genes. Firstly, fix a graph centroid for each hyperedge and according to different associations, and add other nodes related to the graph centroid to hyperedges with a certain probability. Then transform the problem of predicting disease genes into the problem of ranking heterogeneous objects, and the candidate genes are sorted by hypergraph ranking. The method is then applied to the integrated disease gene network. Compared with other prediction methods achieved better results, which was verified by this experiment.

Recent years have witnessed the rapid growth in the number of academics and practitioners who are interested in big scholarly data as well as closely-related areas. Quite a lot of papers reporting recent advancements in this area have been published in leading conferences and journals. Both non-commercial and commercial platforms and systems have been released in recent years, which provide innovative services built upon big scholarly data to the academic community. Examples include Microsoft Academic Graph, Google Scholar, DBLP, arXiv, CiteSeerX, Web of Knowledge, Udacity, Coursera, and edX. The workshop will contribute to the birth of a community having a shared interest around big scholarly data and exploring it using knowledge discovery, data science and analytics, network science, and other appropriate technologies.

Dongyu Zhang, Heting Zhang, Xikai Liu, Hongfei Lin, Feng Xia. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Facial appearance matters in social networks. Individuals frequently make trait judgments from facial clues. Although these face-based impressions lack the evidence to determine validity, they are of vital importance, because they may relate to human network-based social behavior, such as seeking certain individuals for help, advice, dating, and cooperation, and thus they may relate to centrality in social networks. However, little to no work has investigated the apparent facial traits that influence network centrality, despite the large amount of research on attributions of the central position including personality and behavior. In this paper, we examine whether perceived traits based on facial appearance affect network centrality by exploring the initial stage of social network formation in a first-year college residential area. We took face photos of participants who are freshmen living in the same residential area, and we asked them to nominate community members linking to different networks. We then collected facial perception data by requiring other participants to rate facial images for three main attributions: dominance, trustworthiness, and attractiveness. Meanwhile, we proposed a framework to discover how facial appearance affects social networks. Our results revealed that perceived facial traits were correlated with the network centrality and that they were indicative to predict the centrality of people in different networks. Our findings provide psychological evidence regarding the interaction between faces and network centrality. Our findings also offer insights in to a combination of psychological and social network techniques, and they highlight the function of facial bias in cuing and signaling social traits. To the best of our knowledge, we are the first to explore the influence of facial perception on centrality in social networks.

Local administrations and governments aim at leveraging wireless communications and Internet of Things (IoT) technologies to manage the city infrastructures and enhance the public services in an efficient and sustainable manner. Furthermore, they strive to adopt smart and cost-effective mobile applications to deal with major urbanization problems, such as natural disasters, pollution, and traffic congestion. Mobile crowdsourcing (MCS) is known as a key emerging paradigm for enabling smart cities, which integrates the wisdom of dynamic crowds with mobile devices to provide decentralized ubiquitous services and applications. Using MCS solutions, residents (i.e., mobile carriers) play the role of active workers who generate a wealth of crowdsourced data to significantly promote the development of smart cities. In this paper, we present an overview of state-of-the-art technologies and applications of MCS in smart cities. First, we provide an overview of MCS in smart cities and highlight its major characteristics. Second, we introduce the general architecture of MCS and its enabling technologies. Third, we study novel applications of MCS in smart cities. Finally, we discuss several open problems and future research challenges in the context of MCS in smart cities.

With the evolutionary development of latency sensitive applications, delay restriction is becoming an obstacle to run sophisticated applications on mobile devices. Partial computation offloading is promising to enable these applications to execute on mobile user equipments with low latency. However, most of the existing researches focus on either cloud computing or mobile edge computing (MEC) to offload tasks. In this paper, we comprehensively consider both of them and it is an early effort to study the cooperation of cloud computing and MEC in Internet of Things. We start from the single user computation offloading problem, where the MEC resources are not constrained. It can be solved by the branch and bound algorithm. Later on, the multiuser computation offloading problem is formulated as a mixed integer linear programming problem by considering resource competition among mobile users, which is NP-hard. Due to the computation complexity of the formulated problem, we design an iterative heuristic MEC resource allocation algorithm to make the offloading decision dynamically. Simulation results demonstrate that our algorithm outperforms the existing schemes in terms of execution latency and offloading efficiency.

A co-occurrence pattern is an interesting pattern in human mobility, which has essential values in business intelligence, social activities, and urban planning. However, due to the deluge and complexity of mobile big data, as well as the complicated intrinsic features of the co-occurrence pattern, mining and analyzing the co-occurrence pattern are computationally highly expensive. Therefore, in this paper, we propose a framework to mine co-occurrence event data from mobile data and to explore the urban co-occurrence pattern visually. Our framework contains two modules: data modeling, to obtain the co-occurrence event data effectively utilizing frequent itemsets mining algorithm based on traffic GPS records, and visualization, to explore the co-occurrence pattern in urban scenarios from global, regional, statistical, and location perspectives. Our visualization system has been demonstrated using case studies with a real-world data set.

The year of 2017 for the 50th anniversary of the Turing Award, which represents the top-level award in the computer science field, is a milestone. We study the long-term evolution of the Turing Award Collaboration Network, and it can be considered as a microcosm of the computer science field from 1974 to 2016. First, scholars tend to publish articles by themselves at the early stages, and they began to focus on tight collaboration since the late 1980s. Second, compared with the same scale random network, although the Turing Award Collaboration Network has small-world properties, it is not a scale-free network. The reason may be that the number of collaborators per scholar is limited. It is impossible for scholars to connect to others freely (preferential attachment) as the scale-free network. Third, to measure how far a scholar is from the Turing Award, we propose a metric called the Turing Number (TN) and find that the TN decreases gradually over time. Meanwhile, we discover the phenomenon that scholars prefer to gather into groups to do research with the development of computer science. This article presents a new way to explore the evolution of academic collaboration network in the field of computer science by building and analyzing the Turing Award Collaboration Network for decades.

Public transport is of great significance in megacities. Transit-oriented development (TOD) has become a reliable solution to urban sustainable development, which can reshape the urban form and improve its quality. This paper focuses on leveraging heterogeneous mega urban data to answer three critical questions in TOD: what region looks like under TOD concept, which regions have the potential to be TOD regions, and how to construct these TOD regions. For region partition, we propose a connected component-based clustering algorithm, which merges the large amount of public transport stops into representative cluster ones as region centers, and then apply the Voronoi algorithm to locate the region boundaries according to the cluster centers. For TOD region identification, we present a link importance-based random walk method that considers the importance of various transits and further identifies the most valuable regions to be TOD. For discovering functions of TOD regions, we introduce a multifactor-based function characterization approach that combines both the static linguistic factor and human mobility factor together and then derives the actual function distributions. The experiments, which are conducted on three real data sets, show the superiority of the proposed methods to solve the problems of region partition, TOD region identification, and function characterization for the megacities. In the meantime, the results provide support for the government to formulate public policy to construct a TOD city.

It is always difficult for researchers to find a new collaborator due to the academic information overload. Although several scientific collaborator recommendation systems have been proposed, most existing methods cannot meet scholars’ requirements comprehensively due to the neglect of sustainable collaborations in their schemes. Studies have shown that a sustainable collaboration has a significant positive impact on the productivity and influence for a researcher. To address this problem, we develop a sustainable collaborator recommendation (SCORE) system by utilizing the weak tie relationships brought by academic conferences for SCORE. Through defining and quantifying the conference closure, we incorporate the conference coattending relationships into collaborator recommendation system inspired by the principles of “diversified recommendation.” The experimental results on attendees of ten academic conferences show that the SCORE outperforms state-of-the-art collaborator recommendation systems in accuracy and sustainability. Our model can be used to improve the sociability of academic conferences by recommending sustainable collaborators to conference attendees.

Academic team formulation is one of the most critical and fundamental issues in team research. Inspired by the Liebig's metaphor, we formulate an academic team by a barrel composed of planks, namely, Liebig's barrel. We study the capacity of Liebig's barrel from several aspects. Then, we abstract the features in academic teams as those in Liebig's barrel due to the correspondences between team size and plank number, individual member ability and plank height, individual contribution and plank width, allocation of work and plank combination, teamwork attitude and plank tilt angle, team output property, and barrel's content granularity. The investigated model can also be extended to formulate various multifactor objective optimization issues for team science research. In order to verify the rationality of the proposed model, we implement case studies of this model in both the American Physics Society and the Microsoft Academic Graph Computer Science data sets. The experimental results show that the investigated model is effective in academic team formulation. Moreover, an interesting phenomenon is discovered in the proposed model, which we name as the anticask effect that a team's output quality mainly lies on the team member having the maximal research ability rather than those having minimal research ability. We then analyze the underlying reasons for the anticask effect and multiple-factor interaction on academic teams.

Due to the ever-increasing requirements of delay-sensitive and mission-critical applications in 5G, mobile edge computing is promising to react and support real-time interactive systems. However, it is still challenging to construct a 5G-enabled traffic management system, owing to the qualification of ultra-low latency and ubiquitous connectivity. Furthermore, the computing resources and storage capacities of edge nodes are limited, thus computation offloading is a fundamental issue for real-time traffic management. This paper puts forward a hybrid computation offloading framework for real-time traffic management in 5G networks. Specially, we consider both nonorthogonal-multiple-access-enabled and vehicle-to-vehicle-based traffic offloading. The investigated problem is formulated as a joint task distribution, subchannel assignment, and power allocation problem, with the objective of maximizing the sum offloading rate. After that, we prove its NP-hardness and decompose it into three subproblems, which can be solved iteratively. Performance evaluations illustrate the effectiveness of our framework.

The development of smart vehicles brings drivers and passengers a comfortable and safe environment. Various emerging applications are promising to enrich users’ traveling experiences and daily life. However, how to execute computing-intensive applications on resource-constrained vehicles still faces huge challenges. In this article, we construct an intelligent offloading system for vehicular edge computing by leveraging deep reinforcement learning. First, both the communication and computation states are modelled by finite Markov chains. Moreover, the task scheduling and resource allocation strategy is formulated as a joint optimization problem to maximize users’ Quality of Experience (QoE). Due to its complexity, the original problem is further divided into two sub-optimization problems. A two-sided matching scheme and a deep reinforcement learning approach are developed to schedule offloading requests and allocate network resources, respectively. Performance evaluations illustrate the effectiveness and superiority of our constructed system.

Deployment of autonomous Unmanned Aerial Vehicles (UAV) in various sectors such as disaster hit environments, industries, agriculture, etc., not only improves productivity but also reduces human intervention resulting in sustainable benefits. In this regard, we present a model for autonomous navigation and collision avoidance of UAVs in GPS-denied corridor environments. In the first stage, we suggest a fast procedure to estimate the set of parallel lines whose intersection would yield the position of the vanishing point (VP) inside the corridor. A suitable measure is then formulated based on the position of VP on the intersecting lines in reference to any of the image boundary axes. The knowledge of VP location alongside the formulated mechanism govern the necessary set of commands to safely navigate the UAV avoiding any collision with the side walls. Furthermore, the relative Euclidean distance scale expansion of matched scale-invariant keypoints in a pair of frames is taken into account to estimate the depth of a frontal obstacle; usually a wall at the end of the corridor. However, turbulence in the UAV arising due to its rotors or other external factors such as wind may introduce uncertainty in depth estimation. It is rectified with the help of a constant velocity aided Kalman filter model. Necessary set of control commands are then generated to avoid the frontal wall before collision. Exhaustive experiments in different corridors reveal the efficacy of the proposed scheme.

Event-based social networks (EBSNs) are the newly emerging social platforms for users to publish events online and attract others to attend events offline. The content information of events plays an important role in event recommendation. However, the content-based approaches in existing event recommender systems cannot fully represent the preference of each user on events since most of them focus on exploiting the content information from events' perspective, and the bag-of-words model, commonly used by them, can only capture word frequency but ignore word orders and sentence structure. In this paper, we shift the focus from events' perspective to users' perspective, and propose a Deep User Modeling framework for Event Recommendation (DUMER) to characterize the preference of users by exploiting the contextual information of events that users have attended. Specifically, we utilize convolutional neural network (CNN) with word embedding to deeply capture the contextual information of a user's interested events and build up a user latent model for each user. We then incorporate the user latent model into probabilistic matrix factorization (PMF) model to enhance the recommendation accuracy. We conduct experiments on the real-world dataset crawled from a typical EBSN, Meetup.com, and the experimental results show that DUMER outperforms the compared benchmarks.

In recent years, many schemes have been proposed to disseminate Emergency Warning Messages (EWMs) in VANETs. However, various problems such as broadcast storm, hidden terminal and connectivity issues still persist to reduce the efficacy of these systems. In this paper, we propose a novel Social Utility-based Dissemination Scheme (SUDS) for Emergency Warning Messages in Vehicular Social Networks (VSNs). We utilize social properties of nodes such as centrality, interests and friendships to mitigate broadcast storm and hidden terminal problems. Furthermore, we employ the hybrid architecture of VSNs to solve connectivity and contact duration-related issues in sparse and high mobility environments. For this purpose, we devise a dual-strategy-based mechanism, where vehicles communicate with each other in a distributed or centralized manner according to the required situation. In order to evaluate the performance of proposed scheme, we have conducted extensive experiments for a highway scenario under varying vehicular density, vehicular speed and distance, in comparison with the state-of-the-art dissemination schemes. Simulation results have demonstrated the superiority of SUDS over the compared protocols in terms of delivery ratio, transmission delay and total number of transmissions. We have also demonstrated the positive effects of hybrid architecture of VSNs on various network parameters.

Radio frequency identification (RFID) systems can be applied to efficiently identify the missing items by attaching them with tags. Prior missing tag identification protocols concentrated on identifying all of the tags. However, there may be some scenarios in which we just care about the key tags instead of all tags, making it inefficient to merely identify the missing key tags due to the interference of replies from the ordinary tags (i.e., nonkey tags). In this paper, we propose to investigate the problem of efficiently and completely identifying the missing key tags for anonymous RFID systems in which the tag privacy is required to be well protected. First, we propose a vector-based missing key tag identification protocol called VEKI. Then we propose an improved protocol called iVEKI, which consists of two phases: 1) ordinary tag deactivation and 2) missing key tag identification. The parameters of the proposed VEKI and iVEKI protocols are theoretically optimized to maximize the time efficiency. Finally, we conduct extensive simulations to evaluate the proposed VEKI and iVEKI protocols and the simulation results illustrate that they outperform other existing protocols in terms of execution time.

In the new era of integrated computing with intelligent devices and system, moving aerial targets can be tracked flexibly. The estimation performance of traditional matched filter-based methods would deteriorate dramatically for multiple targets tracking, since the weak target is masked by the strong target or the strong sidelobes. In order to solve the problems mentioned above, this paper aims at developing a joint range-Doppler-angle estimation solution for an intelligent tracking system with a commercial frequency modulation radio station (noncooperative illuminator of opportunity) and a uniform linear array. First, a gridless sparse method is proposed for simultaneous angle-range-Doppler estimation with atomic norm minimization. Based on the integrated computing, multiple workstations or servers of the data process center in the intelligent tracking system can cooperate with each other to accelerate the data process. Then a suboptimal method, which estimates three parameters in a sequential way, is proposed based on grid sparse method. The range-Doppler of each target is iteratively estimated by exploiting the joint sparsity in multiple surveillance antennas. A simple beamforming method is used to estimate the angles in turn by exploiting the angle information in the joint sparse coefficients. Simulation result and real test show that the proposed solution can effectively detect weak targets in an iterative manner.

The development requirements of shared buses are extremely urgent to alleviate urban traffic congestions by improving road resource utilization and to provide a neotype transportation mode with good user experiences. The key to shared bus implementation lies in accurately predicting travel requirements and planning dynamic routes. However, the sparseness and the high volatility of shared bus data bring a great resistance to accurate prediction of travel requirements. Based on the consideration of user experiences, optimization objectives of shared bus route planning are significantly different from traditional public transportation and shared bus route planning is far more challenging than online car-hailing services due to the relatively high number of passengers. In this paper, we put forward a two-stage approach (SubBus), which is composed of travel requirement prediction and dynamic routes planning, based on various crowdsourced shared bus data to generate dynamic routes for shared buses in the “last mile” scene. First, we analyze the resident travel behaviors to obtain five predictive features, such as flow, time, week, location, and bus, and utilize them to predict travel requirements accurately based on a machine learning model. Second, we design a dynamic programming algorithm to generate dynamic, optimal routes with fixed destinations for multiple operating buses utilizing prediction results based on operating characteristics of shared buses. Extensive experiments are performed on real crowdsourced shared subway shuttle bus data and demonstrate that SubBus outperforms other methods on dynamic route planning for the “last mile” scene.Note to Practitioners—This paper is inspired by the problem of shared subway shuttle bus dynamic route planning for the “last mile” scene, and it is also applicable to other scenes, including commuting scenes, urban transportation hub scenes, and destination scenes of the tourist market. Shared bus operation routes at such scenes are usually aimed at trips with fixed destinations. Existing approaches to planning routes are generally designed for traditional transportation, such as traditional buses and taxis. In this paper, we propose a novel two-stage dynamic route planning approach (SubBus) based on the operation characteristics of shared subway shuttle buses. We perform a resident travel behavior analysis to improve the accuracy of travel requirement prediction. After that, we combine the prediction results and station properties to gain shared bus optimal routes. We then display how to apply SubBus to optimize shared bus operation status based on crowdsourced shared subway shuttle bus data generated by Panda Bus Company. We keep a continuous collaboration with the company to optimize the approach details and experimental effects, which demonstrate that our approach can generate effective routes for shared subway shuttle buses to optimize operation status on the “last mile” issue.

Context-aware applications of vehicular social networks (VSNs) play a significant role to achieve the goal of green transportation by sharing driving experience to reduce gasoline consumption. One of the main challenges is to evaluate the performance of these applications, which relies on the underlying VSN mobility model. In this paper, we investigate big urban traffic data to characterize essential features of urban mobility and construct large-scale green urban mobility models. We exploit the road and traffic information to enhance the trip generation algorithm and traffic assignment technique based on the weighted segments of roads. Besides, we perform extensive observations and corrections on the OpenStreetMap imported to simulation of urban mobility to make it analogous to real-world road topology. The experimental results and validation process show that the generated mobility models reveal realistic behavior required for analysis of context-aware applications of VSNs for green transportation systems.

Event-based Social Networks (EBSNs) which bridge the gap between online and offline interactions among users have received increasing popularity. The unique cold-start nature makes event recommendation more challenging than traditional recommendation problems, since even for two events with the same content, they may not happen at the same time, the same location, or be organized by the same host. Existing event recommendation algorithms mainly exploit the basic context information (e.g., location, time and content), while the social influence of event hosts and group members have been ignored. In this paper, we propose a Social Information Augmented Recommender System (SIARS), which fully exploits the social influence of event hosts and group members together with basic context information for event recommendation. In particular, we combine the information of EBSNs and other social networks to characterize the social influence of event hosts, and take interactions between group members into consideration for event recommendation. In addition, we propose a new content-aware recommendation model using the topic model to find the most similar topic the event belongs to, and a new location-aware recommendation model integrating location popularity with location distribution for event recommendation. Extensive experiments on real-world datasets demonstrate that SIARS outperforms other recommendation algorithms.

Summary Accurate resource requests prediction is essential to achieve optimal job scheduling and load balancing for cloud Computing. Existing prediction approaches fall short in providing satisfactory accuracy because of high variances of cloud metrics. We propose a deep belief network (DBN)‐based approach to predict cloud resource requests. We design a set of experiments to find the most influential factors for prediction accuracy and the best DBN parameter set to achieve optimal performance. The innovative points of the proposed approach is that it introduces analysis of variance and orthogonal experimental design techniques into the parameter learning of DBN. The proposed approach achieves high accuracy with mean square error of [10−6,10−5], approximately 72%reduction compared with the traditional autoregressive integrated moving average predictor, and has better prediction accuracy compared with the state‐of‐art fractal modeling approach. Copyright © 2016 John Wiley & Sons, Ltd.

With the rapid growth of digital publishing, harvesting, managing, and analyzing scholarly information have become increasingly challenging. The term Big Scholarly Data is coined for the rapidly growing scholarly data, which contains information including millions of authors, papers, citations, figures, tables, as well as scholarly networks and digital libraries. Nowadays, various scholarly data can be easily accessed and powerful data analysis technologies are being developed, which enable us to look into science itself with a new perspective. In this paper, we examine the background and state of the art of big scholarly data. We first introduce the background of scholarly data management and relevant technologies. Second, we review data analysis methods, such as statistical analysis, social network analysis, and content analysis for dealing with big scholarly data. Finally, we look into representative research issues in this area, including scientific impact evaluation, academic recommendation, and expert finding. For each issue, the background, main challenges, and latest research are covered. These discussions aim to provide a comprehensive review of this emerging area. This survey paper concludes with a discussion of open issues and promising future directions.

Recently, urban traffic management has encountered a paradoxical situation which is the empty carrying phenomenon for taxi drivers and the difficulty of taking a taxi for passengers. In this paper, through analyzing the quantitative relationship between passengers' getting on and off taxis, we propose a time-location-relationship (TLR) combined taxi service recommendation model to improve taxi drivers' profits, uncover the knowledge of human mobility patterns, and enhance passengers' travel experience. Moreover, the TLR model uses Gaussian process regression and statistical approaches to acquire passenger volume, mean trip distance, and average trip time in functional regions during every period on weekdays and weekends, and allows drivers to pick up more passengers within a short time frame. Finally, we compare our proposed model with the autoregressive integrated moving average model, the back-propagation neural network model, the support vector machine model, and the gradient boost decision tree model by using the real taxi GPS data in Beijing. The experimental results show that our optimizing taxi service recommendation can predict more accurately than others by considering the 3-D properties.

Stable and reliable wireless communication is one of the critical demands for smart cities to connect people and devices. Although intelligent terminals can be leveraged to deliver and exchange data through Internet, poor network coverage and expensive network access challenge the deployment of network infrastructure. In this paper, we propose a social-oriented smartphone-based adaptive transmission mechanism to improve the network connectivity and throughput in Internet of Things (IoTs) for smart cities. First, a social-oriented double-auction-based relay selection scheme is investigated to stimulate the relay smartphones to forward packets for others so that the network connectivity can be strengthened. Furthermore, for the sake of achieving high throughput in smartphone-based IoTs, the relay method selection is determined by integrating various kinds of transmission schemes in an optimal fashion to make full use of wireless spectrum resource. Due to its high computational complexity, a firefly-algorithm-based scheme is investigated, by which the formulated NP-complete problem can be solved effectively. Simulation results demonstrate the superiority of our proposed method.

Due to the recent proliferation of cyber-attacks, improving the robustness of wireless sensor networks (WSNs), so that they can withstand node failures has become a critical issue. Scale-free WSNs are important, because they tolerate random attacks very well; however, they can be vulnerable to malicious attacks, which particularly target certain important nodes. To address this shortcoming, this paper first presents a new modeling strategy to generate scale-free network topologies, which considers the constraints in WSNs, such as the communication range and the threshold on the maximum node degree. Then, ROSE, a novel robustness enhancing algorithm for scale-free WSNs, is proposed. Given a scale-free topology, ROSE exploits the position and degree information of nodes to rearrange the edges to resemble an onion-like structure, which has been proven to be robust against malicious attacks. Meanwhile, ROSE keeps the degree of each node in the topology unchanged such that the resulting topology remains scale-free. The extensive experimental results verify that our new modeling strategy indeed generates scale-free network topologies for WSNs, and ROSE can significantly improve the robustness of the network topologies generated by our modeling strategy. Moreover, we compare ROSE with two existing robustness enhancing algorithms, showing that ROSE outperforms both.

Scientific article recommender systems are playing an increasingly important role for researchers in retrieving scientific articles of interest in the coming era of big scholarly data. Most existing studies have designed unified methods for all target researchers and hence the same algorithms are run to generate recommendations for all researchers no matter which situations they are in. However, different researchers may have their own features and there might be corresponding methods for them resulting in better recommendations. In this paper, we propose a novel recommendation method which incorporates information on common author relations between articles (i.e., two articles with the same author(s)). The rationale underlying our method is that researchers often search articles published by the same author(s). Since not all researchers have such author-based search patterns, we present two features, which are defined based on information about pairwise articles with common author relations and frequently appeared authors, to determine target researchers for recommendation. Extensive experiments we performed on a real-world dataset demonstrate that the defined features are effective to determine relevant target researchers and the proposed method generates more accurate recommendations for relevant researchers when compared to a Baseline method.

Cooperative data delivery among mobile nodes can improve the performance of data delivery in mobile social networks. However, data routing in the presence of socially selfish (SS) nodes is challenging, where they mitigate the degree of their cooperation level based on their social features and ties to achieve their social objectives. This issue becomes more challenging when they prevent revealing their reactions about incoming messages, which leads data forwarding under uncertain behavior. In this paper, we propose a signaling game approach, namely, Sig4UDD, to study the impact of uncertain cooperation among well-behaved and SS nodes on the performance of data forwarding. In Sig4UDD, we employ Bayesian Nash equilibrium to analyze one-stage interactions among nodes. Then, perfect Bayesian equilibrium is applied to analyze their multistage interactions. In this stage, we establish a belief system to help SS nodes predict the type of their opponents and take appropriate actions to maximize their utilities. To update the beliefs of SS nodes, we devised the weighted social distance metric to measure the global social distance among nodes. Finally, we compare the performance of Sig4UDD to some benchmark cooperative and noncooperative data forwarding protocols using Reality Mining and Social Evolution data sets.

Socially-aware networking is an emerging paradigm for intermittently connected networks consisting of mobile users with social relationships and characteristics. In this setting, humans are the main carriers of mobile devices. Hence, their connections, social features, and behaviors can be exploited to improve the performance of data forwarding protocols. In this paper, we first explore the impact of three social features, namely physical proximity, user interests, and social relationship on users' daily routines. Then, we propose a multi-dimensional routing protocol called Proximity-Interest-Social (PIS) protocol in which the three different social dimensions are integrated into a unified distance function in order to select optimal intermediate data carriers. PIS protocol utilizes a time slot management mechanism to discover users' movement similarities in different time periods during a day. We compare the performance of PIS to Epidemic, PROPHET, and SimBet routing protocols using SIGCOMM09 and INFOCOM06 data sets. The experiment results show that PIS outperforms other benchmark routing protocols with the highest data delivery ratio with a low communication overhead.

To support the sustainable operation of wireless sensor networks using limited energy, duty cycling is a promising solution. However, it is a challenge to guarantee each node communicating with its neighbors under duty cycle when the network is asynchronous. The challenge becomes bigger when nodes’ duty cycles are required to be adjusted separately according to their demands to save energy and achieve high channel utilization. Existing low power listening- and contention-based protocols are not energy-efficient and cannot ensure high channel utility. Additionally, synchronization-based media access control (MAC) protocols suffer from extra energy consumption and low synchronization precision. This paper proposes a localized and on-demand (LOD) duty cycling scheme based on a specifically designed semi-quorum system. LOD can adjust duty cycle of each node adaptively according to its demand so as to avoid channel contention, consequently achieving high channel utilization. This allows the fairness for channel access within asynchronous sensor networks. Extensive experiments are conducted on a real test-bed of 100 TelosB nodes to evaluate the performance of LOD. As compared with B-MAC, LOD substantially reduces contention for channel access and the energy consumption, thus improving the network throughput significantly.

Distributed publish/subscribe systems are poised with challenges of performance degradation and poor scalability. This is typically caused by an uneven load distribution of real-world applications and the susceptibility of link failure in networks. Partitioning and replication techniques have been implemented by exploring community-based load balancing to cope with such issues. The novel approach herein exploits offloading at the inter-community level as well as filter replication at the intra-community level. This results in the dynamic distribution and forwarding of publication and subscription services among brokers during run time. The proposed method, Co-Lab (COmmunity-based LoAd Balancing), seeks to improve the network performance by clustering brokers in a community by taking into consideration interest similarity and filter replication. It attempts to effectively achieve a more consistent and uniform load distribution among brokers and to circumvent the occurrence of highly overloaded brokers. Performance evaluations indicate that Co-Lab has promising advantages by achieving relatively better load balance, reduced overall load and robustness against failures.

editorial Free Access Share on Introduction to: Special Issue on Smartphone-Based Interactive Technologies, Systems, and Applications Editors: James She Hong Kong University of Science & Technology, Hong Kong Hong Kong University of Science & Technology, Hong KongView Profile , Alvin Chin BMW Group, United States BMW Group, United StatesView Profile , Feng Xia Dalian University of Technology, China Dalian University of Technology, ChinaView Profile , Jon Crowcroft University of Cambridge, UK University of Cambridge, UKView Profile Authors Info & Claims ACM Transactions on Multimedia Computing, Communications, and ApplicationsVolume 12Issue 1sArticle No.: 11pp 1–4https://doi.org/10.1145/2820398Published:21 October 2015Publication History 4citation201DownloadsMetricsTotal Citations4Total Downloads201Last 12 Months18Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

While visualization has been widely used as a data presentation tool in both desktop and mobile devices, the rapid visualization of information from images is still underexplored. In this work, we present a smartphone image acquisition and visualization approach for text-based data. Our prototype, ShotVis, takes images of text captured from mobile devices and extracts information for visualization. First, scattered characters in the text are processed and interactively reformulated to be stored as structured data (i.e., tables of numbers, lists of words, sentences). From there, ShotVis allows users to interactively bind visual forms to the underlying data and produce visualizations of the selected forms through touch-based interactions. In this manner, ShotVis can quickly summarize text from images into word clouds, scatterplots, and various other visualizations all through a simple click of the camera. In this way, ShotVis facilitates the interactive exploration of text data captured via cameras in smartphone devices. To demonstrate our prototype, several case studies are presented along with one user study to demonstrate the effectiveness of our approach.

Mobile devices, especially smartphones are increasingly gaining ground in several domains, particularly healthcare, tele-monitoring, and education to perform Resource-intensive Mobile Applications (RiMA). However, constrained resources, especially CPU and battery hinder their successful adoption. Mobile Cloud Computing (MCC) aims to augment computational capabilities of resource-constraint mobile devices and conserve their native resources by remotely performing intensive tasks. In typical MCC solutions, intensive tasks are offloaded to distant VM-based cloud data centers or cloudlets whose exploitation originates long WAN latency and/or virtualization overhead degrading RiMA execution efficiency. In this paper, a lightweight Resource-oriented MCC (RMCC) architecture is proposed that exploits resources of plethora of Adjacent Service-based Mobile Cloudlets (ASMobiC) as fine-grained mobile service providers. In RMCC, ASMobiCs host prefabricated Restful services to be asynchronously called by mobile service consumers at runtime. RMCC is a Restful cross-platform architecture functional on major mobile OSs (e.g., Android and iOS) and realizes utilization of the computing resources of off-the-shelve outdated or damaged-yet-functioning mobile devices towards green MCC. Results of benchmarking advocate significant mean time- and energy-saving of 87% and 71.45%, respectively when intensive tasks are executed in ASMobiCs.

In data management protocols for Ad-hoc Social Networks (ASNETs), involvement of selfish users can pose a serious threat to network performance and fairness. Therefore, it is essential to detect and mitigate their effects on other well behaving users. We contribute to this line of research by combining the benefits of users' social behavior (social tie) with a biologically inspired approach in ASNETs. We designed a bio-inspired scheme (BoDMaS) to detect and mitigate selfish users in replication operations. Its goals include providing greater accessibility and effective detection of selfish users. The proposed scheme not only guarantees accessibility and effective detection rate, but also ensures the reliability of replica allocation operations.

Reliable social connectivity and transmission of data for popular nodes are vital in multihop Ad-hoc Social Networks (ASNETs). However, congestion may occur and hence popular nodes might not achieve required bandwidth when multiple senders share data with a single receiver. The traditional Transport Control Protocol (TCP) might not be able to perform efficiently in ASNETs. Therefore, we propose a Reliable TCP for Popular Data in Socially-aware Ad-hoc Networks called RTPS. RTPS employs a popularity level approach for every single node which partitions the bandwidth among users. The reliability of popular data is ensured since bandwidth will firstly assigned to the popular sender. Preliminary results show that by delaying the acknowledgment and improving the performance of TCP, RTPS reduces collision loss in multihop ASNETs.

To address selfishness in socially-aware networking, we propose a Community-based Incentive Scheme (CIS). CIS utilizes community to stimulate cooperation among selfish nodes and allows all nodes to behave selfishly to imitate the realistic condition. The simulation results show that CIS effectively stimulates selfish nodes to cooperate, achieves higher delivery ratio while not increasing latency dramatically.

This paper addresses recommending presentation sessions at smart conferences to participants. We propose a venue recommendation algorithm: socially aware recommendation of venues and environments (SARVE). SARVE computes correlation and social characteristic information of conference participants. In order to model a recommendation process using distributed community detection, SARVE further integrates the current context of both the smart conference community and participants. SARVE recommends presentation sessions that may be of high interest to each participant. We evaluate SARVE using a real-world dataset. In our experiments, we compare SARVE with two related state-of-the-art methods, namely context-aware mobile recommendation services and conference navigator (recommender) model. Our experimental results show that in terms of the utilized evaluation metrics, i.e., precision, recall, and f-measure, SARVE achieves more reliable and favorable social (relations and context) recommendation results.

Replication is an important mechanism in modern wireless networks and has attracted significant efforts to improve its performance with different metrics including read cost, consistency and relocation cost. Traditionally, different ideal approaches are widely used to facilitate data availability. However, the quality of wireless links would be affected by many factors like mobility and overhead. The accessibility and reliability of Ad-hoc Social Network (ASNET) services can be assured by replication approaches. It is used to increase data availability by replicating data items locally or nearby. In ASNETs, replication helps to avoid data losses in case of an unpredictable group mobility that causes community partition and also aids in reducing the number of hops when a data is transmitted from source to destination. A new data replication method called ComPAS (community-partition aware replica allocation method) is proposed in this paper. This method can significantly improve ASNETs performance by exploiting social relationship while replicating in the community to achieve better efficiency and consistency while keeping the replica relocation cost as low as possible. This type of replica allocation method will increase the availability of different data items in a partitioned social community. Evaluation results verify the effectiveness of the method.

Socially-aware networking provides a promising paradigm for data forwarding by exploiting the involved nodes' social properties in mobile social networks. However, individuals' learning capability and awareness to the dynamic environment have not been well explored in the literature. In this paper, we give a brief introduction of an interest-based scheme called BEEINFO. Inspired by swarm intelligence, BEEINFO takes advantage of individuals' perceiving and learning capability to gather information of density and social tie during communication. Moreover, it classifies communities based on nodes' interests and distinguishes data forwarding into situations of inter-community and intra-community. Furthermore, BEEINFO performs efficient message scheduling and buffer management to improve performance. The simulation results show that BEEINFO outperforms PROPHET and Epidemic in message delivery ratio, overhead and hop count, except for average latency.

With the aim of prolonging network lifetime, many energy efficient algorithms and data dissemination protocols have been proposed for wireless sensor networks (WSNs) recently. Since sensor nodes close to sink have to bear more traffic burden to forward data, they will quickly deplete their energy which leads to energy hole and network partition problem. Adding mobility into sensor networks brings in new opportunities to improve network performance in terms of energy consumption, network lifetime, latency etc. In this paper, our Mobility based Data Collection Algorithm (MDCA) for Wireless Sensor Networks is proposed. Multiple mobile sinks are utilized, instead of one static sink, to move back and forth along predetermined paths to collect data. One of the predetermined paths is the diameter of the circle area and the other two are fixed on arc lines. The mobile sinks only sojourn at some fixed points to collect data from relevant areas. The effectiveness of our proposed algorithm is demonstrated through extensive simulation results.

In the field of linked data, interlinking previously unlinked datasets that are available on the linked open cloud is still a big challenge. Silk is one of the tools that allow one to do interlinking between data items within different linked data sources. The main goal of our work is to simplify the process of specifying linking conditions using Silk. Specifying the correct conditions in the Silk-LSL is a complex task where a helpful interface can make a large difference. In this work, we propose Silk Magic as a useful tool that is capable of guiding the users through the process of specifying linking conditions during the creation of the Silk LSL program and hence simplifies the task of writing Silk-LSL programs. The tool for example allows to display the conditions as an interactive tree, and offers suggestions for class selection conditions and step expressions in path expressions.

The complexity of real-world industrial control systems is growing rapidly. This raises significant challenges for the use of embedded systems in control applications, since embedded platforms are generally resource limited. In this work we develop a Scilab/Scicos based embedded controller on which various control software can be easily modeled, simulated, implemented, and evaluated to meet the ever-expanding requirements of complex industrial control applications. It is built on the Cirrus Logic EP9315 ARM9 systems-on-chip board. With the developed platform, it is possible to design and implement complex embedded control systems that employ advanced control strategies in a rapid and cost-efficient fashion. Thanks to the free and open source nature of the software packages used, the cost of the embedded controller is minimized.

Modern manufacturing companies need flexible manufacturing control systems (FMCSs) to compete in today's unpredictable and ever-changing global markets. Traditional methodologies, however, can't meet the requirements of FMCS design. The function block (FB) concept in IEC61499 may provide a promising approach. In this present work, a FB based design pattern has been introduced to systematize the task of FMCS design in the IEC61499 context, which is enhanced by adopting formal reference models in the design cycle. The FB based framework and engineering methodology have been proposed, together with requirements specification of CASE tools to facilitate the development process. An illustrative example using the proposed design pattern is presented. When properly applied, it can substantially reduce the time and cost of systems engineering, while enhancing the flexibility, modularity, extensibility, reusability and interoperability of FMCSs.