Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting expressiveness, they also expose new vulnerabilities in graph learning through text-based adversarial surfaces. Recent advances leverage diverse backbones, such as graph neural networks (GNNs) and pre-trained language models (PLMs), to capture both structural and textual information in TAGs. This diversity raises a key question: How can we design universal adversarial attacks that generalize across architectures to assess the security of TAG models? The challenge arises from the stark contrast in how different backbones—GNNs and PLMs—perceive and encode graph patterns, coupled with the fact that many PLMs are only accessible via APIs, limiting attacks to black-box settings. To address this, we propose BadGraph, a novel attack framework that deeply elicits large language models' (LLMs) understanding of general graph knowledge to jointly perturb both node topology and textual semantics. Specifically, we design a target influencer retrieval module that leverages graph priors to construct cross-modally aligned attack shortcuts, thereby enabling efficient LLM-based perturbation reasoning. Experiments show that BadGraph achieves universal and effective attacks across GNN- and LLM-based reasoners, with up to a 76.3% performance drop, while theoretical and empirical analyses confirm its stealthy yet interpretable nature.

Explaining the decision-making process of Graph Neural Networks (GNNs) is essential for improving their transparency and reliability. However, real-world graphs are often heterogeneous and subject to structural noise, posing severe challenges to the robustness of existing explanation methods. To address these issues, we propose RoHeX, a Robust Heterogeneous GNN Explainer that enhances explanation quality under noisy conditions. RoHeX begins with a theoretical analysis revealing how different heterogeneous GNN architectures amplify structural perturbations through message passing. Building on this insight, we design a denoising variational inference framework that filters noisy structures and learns robust latent graph representations. Furthermore, we incorporate relation-aware heterogeneous semantics into the explanation generation process, formulating explanation as an optimization problem under the graph information bottleneck principle. This formulation enables RoHeX to balance fidelity and compactness, producing explanations that are both semantically meaningful and structurally stable. Comprehensive experiments on multiple real-world heterogeneous graphs demonstrate that RoHeX consistently surpasses state-of-the-art baselines in explanation fidelity, robustness to structural perturbations, and explainability.

Label flipping attacks stand as a potent and practical threat to the integrity of machine learning models. While extensive research has focused on designing sophisticated attack and defense mechanisms, the underlying factors that govern a model's susceptibility remain underexplored. This paper reveals a critical phenomenon: the impact of label flipping attacks is highly differential across classes, strongly correlated with the intrinsic confusability between the source and target classes. We provide a rigorous theoretical analysis, demonstrating that a lower standardized separation between classes fundamentally leads to greater vulnerability. Grounded in this insight, we propose Confusability-Aware Contrastive Learning (CACL), a targeted defense that maximizes the feature-space separation for the most vulnerable class pairs. Extensive experiments validate the strong link between class separability and vulnerability, and show that CACL significantly mitigates the attack's impact while providing superior protection for the most susceptible classes. Our code is available at https://github.com/Pinlong-Zhao/Unequal-Vulnerability.

Integrated Sensing and Communication (ISAC) systems are playing an increasingly crucial role in modern wireless networks. However, in the ISAC scenario, the high transmission power required for communicating and sensing signals poses an increased risk of signal interception by eavesdroppers. To address this issue and enhance the physical layer security (PLS) of ISAC, we utilize Reconfigurable Intelligent Surfaces (RIS) to optimize the secrecy rate in the ISAC context, improving link security and effectively preventing eavesdropping. In the ISAC scenario, the location of the eavesdropper can be obtained through sensing. Leveraging this advantage, we employ Graph Neural Networks (GNN) to aggregate the node information of users and eavesdroppers, which iteratively passes messages and updates node states, thereby adaptively optimizing the transmitting beamforming vector and the RIS phase shift matrix. Simulation results show that this method is superior to the benchmark algorithm.

The utilization of graph neural networks in heterogeneous networks has been rapidly increasing in recent years. The topological structure, fundamental to the nature of graphs, is often claimed to be jointly addressed with attribute information by most heterogeneous graph neural network (HGNN) approaches. However, this assertion lacks sufficient empirical validation. We empirically challenge these claims within existing evaluation frameworks. We propose a straightforward multi-layer perceptron (MLP) based model which relies solely on adjacency relationships for feature aggregation, without fully exploiting the graph's intricate topological structures. Unexpectedly, the model achieved nearly state-of-the-art performance on several real-world datasets. This discrepancy indicates that current evaluation protocols contain systemic biases and often fail to distinguish superficial adjacency exploitation from genuine structural pattern learning. It also points to the need for future benchmark datasets and metrics that more faithfully reflect the real requirements of topological learning. We hope this work stimulates further research into the role and significance of topological information in HGNNs.

Most network embedding (NE) methods are either based on the proximity for community-guided tasks or on the structural similarity for role-oriented tasks. While being prevalent and effective, there still exists some potential issues that need further attention: 1) community and role are always regarded as orthogonal problems. They have rarely been combined to model the latent structures within the complex network. However, the generation of the network is usually jointly driven by these two mechanisms; and 2) few works study the interaction between roles or communities, which leads to the generation process of the network cannot being effectively modeled. To solve these problems, we propose a unified network embedding framework via mutual fusion of community and role (UMFCR). We combine the Gaussian mixture model (GMM) with a variational graph auto-encoder to generate node embeddings and discover the membership distribution of each node. An elaborate fusion pattern is then designed to produce the generation process for each link from the perspective of both community and role. The promising experimental results on real-world data demonstrate the necessity of fusing these two mechanisms and the superior performance of the model on different network tasks.

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

Multivariate time series anomaly detection has numerous real-world applications and is being extensively studied. Modeling pairwise correlations between variables is crucial. Existing methods employ learnable graph structures and graph neural networks to explicitly model the spatial dependencies between variables. However, these methods are primarily based on prediction or reconstruction tasks, which can only learn similarity relationships between sequence embeddings and lack interpretability in how graph structures affect time series evolution. In this paper, we designed a framework that models spatial dependencies using interpretable causal relationships and detects anomalies through changes in causal patterns. Specifically, we propose a method to dynamically discover Granger causality using gradients in nonlinear deep predictors and employ a simple sparsification strategy to obtain a Granger causality graph, detecting anomalies from a causal perspective. Experiments on real-world datasets demonstrate that the proposed model achieves more accurate anomaly detection compared to baseline methods.

Graph Neural Networks (GNNs) have demonstrated remarkable capabilities in handling graph data. Typically, GNNs recursively aggregate node information, including node features and local topological information, through a message-passing scheme. However, most existing GNNs are highly sensitive to neighborhood aggregation, and irrelevant information in the graph topology can lead to inefficient or even invalid node embeddings. To overcome these challenges, we propose a novel Space Gravity-based Graph Neural Network (Gravity-GNN) guided by Deep Reinforcement Learning (DRL). In particular, we introduce a novel similarity measure called ''node gravity'', inspired by the gravitational force between particles in space, to compare nodes within graph data. Furthermore, we employ DRL technology to learn and select the most suitable number of adjacent nodes for each node. Our experimental results on various real-world datasets demonstrate that Gravity-GNN outperforms state-of-the-art methods regarding node classification accuracy, while exhibiting greater robustness against disturbances.

Biometrics is one of the most prominent sources of knowledge for human identification in the rapidly advancing field of cybersecurity. Among various types of biometric information, electrocardiogram (ECG) and photoplethysmography (PPG) signals gained considerable attention due to its inherent resistance to spoofing. However, existing researches are predominantly conducted in controlled environments, where ECG or PPG signals are susceptible to interference from motion and noise in real-world scenarios, resulting in suboptimal model robustness. Additionally, the few multimodal ECG identification studies mainly based on different conversion methods of ECG signal, resulting in information redundancy between modalities. To address these, we propose a lightweight identity recognition model based on cross-domain multimodal feature fusion of ECG and PPG signals. It incorporates an enhanced MultiRes block that forwards upsampled data for multi-resolution analysis of signal features, and employs spatial pyramid pooling for multi-scale feature extraction. Using this network structure, we separately extract and fuse features from ECG and PPG signals, then perform identity recognition based on the fused features. Extensive experiments were conducted to evaluate the proposed algorithm. The proposed fusion model reaches a high accuracy of 97.26%, improving by 17.06% and 40.48% compared to single-modal ECG and PPG identification models, respectively. By visualizing the fused features alongside single-modal ECG and PPG features, we intuitively explain the effectiveness of multimodal feature fusion for feature extraction, offering a new approach for multimodal biometric recognition.

Temporal interaction graphs (TIGs), defined by sequences of timestamped interaction events, have become ubiquitous in real-world applications due to their capability to model complex dynamic system behaviors. As a result, temporal interaction graph representation learning (TIGRL) has garnered significant attention in recent years. TIGRL aims to embed nodes in TIGs into low-dimensional representations that effectively preserve both structural and temporal information, thereby enhancing the performance of downstream tasks such as classification, prediction, and clustering within constantly evolving data environments. In this paper, we begin by introducing the foundational concepts of TIGs and emphasizing the critical role of temporal dependencies. We then propose a comprehensive taxonomy of state-of-the-art TIGRL methods, systematically categorizing them based on the types of information utilized during the learning process to address the unique challenges inherent to TIGs. To facilitate further research and practical applications, we curate the source of datasets and benchmarks, providing valuable resources for empirical investigations. Finally, we examine key open challenges and explore promising research directions in TIGRL, laying the groundwork for future advancements that have the potential to shape the evolution of this field.

The pre-training and fine-tuning methods have gained widespread attention in the field of heterogeneous graph neural networks due to their ability to leverage large amounts of unlabeled data during the pre-training phase, allowing the model to learn rich structural features. However, these methods face the issue of a mismatch between the pre-trained model and downstream tasks, leading to suboptimal performance in certain application scenarios. Prompt learning methods have emerged as a new direction in heterogeneous graph tasks, as they allow flexible adaptation of task representations to address target inconsistency. Building on this idea, this paper proposes a novel multi-task prompt framework for the heterogeneous graph domain, named HGMP. First, to bridge the gap between the pre-trained model and downstream tasks, we reformulate all downstream tasks into a unified graph-level task format. Next, we address the limitations of existing graph prompt learning methods, which struggle to integrate contrastive pre-training strategies in the heterogeneous graph domain. We design a graph-level contrastive pre-training strategy to better leverage heterogeneous information and enhance performance in multi-task scenarios. Finally, we introduce heterogeneous feature prompts, which enhance model performance by refining the representation of input graph features. Experimental results on public datasets show that our proposed method adapts well to various tasks and significantly outperforms baseline methods.

Graph federated learning (GFL) is increasingly utilized in domains such as social network analysis and recommendation systems, where non-IID data exist extensively and necessitate a strong emphasis on personalized learning. However, existing methods focus only on the personality among different clients instead of the personality within a client which widely exists in the real social networks, where intra-client personality addresses the heterogeneity of known data, while inter-client personality always tackle client heterogeneity under privacy constraint. In this paper, we propose a novel automatic personalized graph federated learning (PGFL) scheme named FedCCH to capture both inter-client and intra-client heterogeneity. For intra-client heterogeneity, we innovatively propose the learnable Personalized Factor (PF) to automatically normalize each graph representation within clients by learnable parameters, which weakens the impact of non-IID data distribution. For inter-client heterogeneity, we propose a novel hash-based similarity clustering method to generate the hash signature for each client, and then group similar clients for joint training among different clients. Ultimately, we collaboratively train intra-client and inter-client modules to improve the effectiveness of capturing the heterogeneity of the graph data of clients. Experiment results demonstrate that FedCCH outperforms other state-of-the-art baseline methods.

Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal graphs (HTGs) have been proposed and have achieved successful applications in various fields. However, most existing GRL methods mainly focus on preserving the low-order topology information while ignoring higher-order group interaction relationships, which are more consistent with real-world networks. In addition, most existing hypergraph methods can only model static homogeneous graphs, limiting their ability to model high-order interactions in HTGs. Therefore, to simultaneously enable the GRL model to capture high-order interaction relationships in HTGs, we first propose a formal definition of heterogeneous temporal hypergraphs and P-uniform heterogeneous hyperedge construction algorithm that does not rely on additional information. Then, a novel Heterogeneous Temporal HyperGraph Neural network (HTHGN), is proposed to fully capture higher-order interactions in HTGs. HTHGN contains a hierarchical attention mechanism module that simultaneously performs temporal message-passing between heterogeneous nodes and hyperedges to capture rich semantics in a wider receptive field brought by hyperedges. Furthermore, HTHGN performs contrastive learning by maximizing the consistency between low-order correlated heterogeneous node pairs on HTG to avoid the low-order structural ambiguity issue. Detailed experimental results on three real-world HTG datasets verify the effectiveness of the proposed HTHGN for modeling high-order interactions in HTGs and demonstrate significant performance improvements.

Heterogeneous Graph Neural Networks (HGNNs) are vulnerable, highlighting the need for tailored attacks to assess their robustness and ensure security. However, existing HGNN attacks often require complex retraining of parameters to generate specific perturbations for new scenarios. Recently, foundation models have opened new horizons for the generalization of graph neural networks by capturing shared semantics across various graph distributions. This leads us to ask: Can we design a foundation attack model for HGNNs that enables generalizable perturbations across different HGNNs, and quickly adapts to new heterogeneous graphs (HGs)? Empirical findings reveal that, despite significant differences in model design and parameter space, different HGNNs surprisingly share common vulnerability patterns from a relation-aware perspective. Therefore, we explore how to design foundation HGNN attack criteria by mining shared attack units. In this paper, we propose a novel relation-wise heterogeneous graph foundation attack model, HeTa. We introduce a foundation surrogate model to align heterogeneity and identify the importance of shared relation-aware attack units. Building on this, we implement a serialized relation-by-relation attack based on the identified relational weights. In this way, the perturbation can be transferred to various target HGNNs and easily fine-tuned for new HGs. Extensive experiments exhibit powerful attack performances and generalizability of our method.

Role discovery assist in various applications of online social networks, such as water army detection, shopping recommendation, rumor tracing, etc. However, existing studies often overlook the significance of hierarchical structures in online social networks, which are crucial for understanding the roles played by different users. To address this gap, we propose a novel approach based on hyperbolic graph learning, called HyperRole, which effectively leverages the hierarchical structure of online social networks for role discovery. HyperRole first extracts structural features from users and constructs user sequences based on feature similarity, capturing the relationships between users across different scales. Then, we learn role information from structural features by hyperbolic graph Transformer to embed users into the hyperbolic space, preserving the hierarchical structure between users and enabling interactions between users of the same level that are far away from each other. Additionally, we leverage the hierarchical distance between the target user and other users within the same sequence to guide and modify the role information of the target user. Based on the generated user role embeddings, we train a multi-class classifier to classify roles. Extensive experiments on several real-world network datasets demonstrate that our model outperforms existing baseline methods, showcasing its superior performance.

Biomedical event extraction, a cornerstone of information extraction, has increasingly attracted attention within the biomedical research community. Moreover, it is a highly complex task, which not only deals with many sub-tasks but also involves nested events. Currently, the research on biomedical event extraction, whether pipelined model or joint method, needs to be processed for each sub-task. The process of processing each sub-task one by one lead to the degradation of event extraction performance. In addition, most studies focus on extracting sentence-level events and ignore cross-sentence event information. To solve these problems, we simplify the process of event extraction, reduce the processing steps, and combine the two sub-tasks of relation extraction and argument combination as one sub-task. In addition, we consider document-level event extraction, which not only extracts cross-sentence events but also considers broader context information. Experimental results indicate that our novel approach outperforms prior studies. Additionally, the document-level event extraction model attains the top performance on the BioNLP’11 test data and achieves near-leading performance on the BioNLP’13 test data.

The Heterogeneous Information Network (HIN) stands out as a prominent tool for depicting interactions in real-world systems. Recently, representation learning on HINs has attracted significant attention, as the structured and compact output embeddings offer great convenience for network analysis and graph machine learning tasks. While existing HIN representation learning methods excel in supervised training or direct proximity reconstruction, yielding satisfactory performance in tasks like node clustering and classification, they often overlook the critical HIN generative process characterized by numerous events. As a result, these methods fail to preserve the higher-order interactions among the nodes and predict potential links in HINs. To address these limitations, we propose a Contrastive Learning method via Events on Heterogeneous Information Networks (CLEH). CLEH delineates the generative process from the local structure (nodes) to the higher-order structure (events) in HINs. We design a novel event-level contrastive learning procedure, endowing representations with the capability to capture higher-order relations among nodes. Moreover, CLEH leverages a normalizing flow model as the encoder to enhance the expressiveness of embeddings. Experimental results on HIN datasets demonstrate the significant superiority of CLEH in link prediction compared to popular baselines.

Information diffusion and diffusion prediction have attracted a great deal of research attention over the past decades. Existing approaches usually make predictions based on the order of the activated users, while recently, some studies have taken the social network into consideration and begun to analyze the influence of neighbors via some graph neural networks. However, they ignore the fact that the interests of users and their neighbors may dynamically change along with the growth of the cascade, and thus fail to model the potential impact of activated users. To address the above shortcomings, we proposed in this paper a deep learning model that combines theMode of cascadesGrowth and potentialImpact of users (MGI). It leverages GCNs to represent users from the social network to model their static features. Besides, we designed an attention mechanism on the cascade sequence to compute features of activated users, and added the popularity variable to model features of users in cascades. Finally, we combined the growth of cascades and impact of users in our model for diffusion prediction. We conducted extensive experiments on several real-world datasets, and the experimental results demonstrate that our model significantly outperforms the state-of-the-art methods in diffusion prediction.

Network alignment, which integrates multiple network resources by identifying anchor nodes that exist in different networks, is beneficial for conducting comprehensive network analysis. Although there have been many studies on network alignment, most of them are limited to static scenarios and only can achieve acceptable top-$\alpha$($\alpha \gt 10$) results. In the absence of considering dynamic changes in networks, accurate network alignment (i.e., top-1 result) faces two problems: 1) Missing information: focusing solely on aligning networks at a specific time leads to low top-1 performance due to the lack of information from other time periods; 2) Confusing information: ignoring temporal information and focusing on aligning networks across the entire time span leads to low top-1 performance due to inability to distinguish the neighborhood nodes of anchor nodes. In this paper, we propose a dynamic network alignment method, which aims to achieve better top-1 alignment results with consider changing network structures over time. Towards this end, we learn the representations of nodes in the changing network structure with time, and preserve the consistency of anchor node pairs during the time-evolution process. Firstly, we employ a Structure-Time-aware module to capture network dynamics while preserving network structure and learning node representations that incorporate temporal information. Secondly, we ensure the global and local consistency of anchor node pairs over time by utilizing linear and similarity functions, respectively. Finally, we determine whether two nodes are anchor node pairs by maintaining consistency between global, local, and node representations. Experimental results obtained from real-world datasets demonstrate that the proposed model achieves performance comparable to several state-of-the-art methods.

Joint Vehicle-to-vehicle (V2V) and Vehicle-to-Infrastructure (V2I) offloading presents an efficient approach to leverage surplus computing resources from neighboring devices, thereby expanding the coverage of computing resources supply in the context of the Internet of Vehicles. However, many studies overlook the significance of topological communications caused by the rapid movement of vehicles, privacy, and communication intentions. To achieve efficient task offloading when facing various topological link structures, we first propose a novel topological link-aware task co-offloading (TLCO) method designed for partially offloading in the joint V2V and V2I system. Next, we model the sequential subtasks offloading process as the Markov Decision Process (MDP) and utilize the Double Deep Q-Network (DDQN) algorithm to optimize the total delay of the proposed system. Additionally, we put forth a prediction framework named Sliding Time Windows and TLCO algorithm (STW-TLCO) to accurately forecast the computation load at various time windows using pulsed parameters. Extensive experimental results demonstrate the effectiveness and superiority of the proposed TLCO-DDQN algorithm in comparison to other Deep Reiforcement Learning (DRL)-based and Greedy-based approaches. Furthermore, the STW-TLCO algorithm exhibits high accuracy, with an R-squared value exceeding 96%, confirming its predictive capabilities.

The unique capabilities of Unmanned Aerial Vehicles (UAVs), including their superior mobility, flexibility, and line-of-sight transmission, have made them well-suited for facilitating Aerial Edge Computing (AEC). This computing paradigm is particularly beneficial for meeting the computing demands of User Equipments (UEs) in emergency situations, as it offers efficient support for task offloading. Considering the service requirements of UEs, it is essential to minimize the processing delay experienced by UEs in AEC systems. This is accomplished through the joint optimization of the UAV trajectory, flight speed, and task offloading ratio allocation for UEs. Due to the non-convex nature and the continuous action space of the problem, recent studies have turned to the Deep Deterministic Policy Gradient (DDPG) to tackle similar challenges. However, Deep Neural Networks (DNNs) employed in DDPG are limited to extracting latent information solely from Euclidean data, and are similarly constrained by the highly dynamic changes in channel states within AEC networks, thereby disregarding the valuable features inherent in the structural information. In order to alleviate the task offloading problem in AEC systems, we propose a novel Graph Convolutional Pooling-DDPG (GCP-DDPG) algorithm by exploiting the graph-based multi-relational derivation capability of the multi-Relational Graph Convolutional Network (R-GCN) and employing the reinforcement learning technique. Extensive simulation experiments are conducted to evaluate the superiority and effectiveness of the GCP-DDPG algorithm. The results demonstrate a remarkable performance improvement of 34.6% compared to state-of-the-art approaches.

Although contrastive self-supervised learning (SSL) on dynamic graphs has made significant success, the issue of heavy reliance on data augmentation and training tricks has been a persistent pain point. Generative SSL, especially masked autoencoders (MAEs) have recently produced promising results and can avoid these issues. However, the research on MAE in dynamic graphs remains largely unexplored due to the following challenges: 1) how to design an effective masking strategy for dynamic graphs? and 2) how to design a decoder to retain temporal dependency when graphs are perturbed? In this article, we propose DVGMAE, a novel dynamic variational graph masked autoencoder model to solve these challenges. DVGMAE simultaneously captures the evolving behaviors and topological features via an innovative masking strategy and an elaborate decoder. Specifically, we first implement a temporal-aware masking strategy on the edges of each snapshot based on the updated probabilities derived from historical mask information. This strategy mitigates potential masking bias in dynamic graphs. We then design a globally enhanced decoder to recover the temporal and spatial information of each snapshot. Extensive experiments demonstrate that DVGMAE outperforms the existing state-of-the-art on various tasks across different datasets.

The task of network alignment aims to identify corresponding nodes across multiple networks, with applications in various fields such as social network analysis and bioinformatics. Traditional methods typically focus on the topological structure of networks at a specific level, but they may overlook important properties exhibited by many networks, such as scale-free properties and specific power-law structures often found in social networks. Consequently, these methods fail to effectively capture and utilize such information, leading to misalignment. In this article, we propose a network alignment framework that incorporates both topological and attribute information from multiple levels in the network, including homogeneity, power-law, and higher order structures. We introduce a Euclidean hyperbolic interactive graph learning method specifically designed for modeling power-law structures in networks, aiming to improve the accuracy of network alignment. To evaluate the effectiveness of our proposed method, we conduct experiments on several real-world datasets. The results demonstrate that our approach achieves higher accuracy compared to other advanced baselines.

Network alignment is a fundamental problem in various domains since it can establish bridges for the same entity (i.e., anchor nodes) between different networks. Most existing network alignment methods are based on consistency assumption, i.e., anchor nodes exhibit similar local structures or neighbors across different networks. However, many anchor nodes have different local structures or neighbors across different networks, which could be regarded as anchor nodes' heterogeneity. It poses a challenge to methods based on the assumption of consistency, as they lack abundant shared information, such as common neighbors. Fortunately, network communities provide the comprehension of node relationships and group structures within networks, which could alleviate the information insufficient. In this article, we propose to address the challenge of inadequate shared information triggered by nodes' heterogeneity from a community perspective. Our model is based on joint optimization of node representation learning and community discovery, including: 1) a node-level constraint is employed to bring nodes with more anchor pairs as neighbors closer together and 2) a community-level constraint is utilized to bring nodes with higher order similarity closer together. We model the cross-network community alignment relations as asymmetric to mitigate the interference caused by anchor node heterogeneity when measuring community alignment relations. Furthermore, we leverage the learned cross-network community alignment relations to supplement node alignment, which could narrow down the search range of potential anchor nodes by focusing solely on aligning nodes within aligned cross-network communities. We conducted extensive experiments on real-world datasets, and the results show the effectiveness and efficiency of our proposed model on network alignment.

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

Reconfigurable intelligent Surfaces (RIS) and half-duplex decoded and forwarded (DF) relays can collaborate to optimize wireless signal propagation in communication systems. Users typically have different rate demands and are clustered into groups in practice based on their requirements, where the former results in the trade-off between maximizing the rate and satisfying fine-grained rate demands, while the latter causes a trade-off between inter-group competition and intra-group cooperation when maximizing the sum rate. However, traditional approaches often overlook the joint optimization encompassing both of these trade-offs, disregarding potential optimal solutions and leaving some users even consistently at low date rates. To address this issue, we propose a novel joint optimization model for a RIS- and DF-assisted multiple-input single-output (MISO) system where a base station (BS) is with multiple antennas transmits data by multiple RISs and DF relays to serve grouped users with fine-grained rate demands. We design a new loss function to not only optimize the sum rate of all groups but also adjust the satisfaction ratio of fine-grained rate demands by modifying the penalty parameter. We further propose a two-phase graph neural network (GNN) based approach that inputs channel state information (CSI) to simultaneously and autonomously learn efficient phase shifts, beamforming, and relay selection. The experimental results demonstrate that the proposed method significantly improves system performance.

Information diffusion prediction plays a crucial role in understanding the propagation of information in social networks, encompassing both macroscopic and microscopic prediction tasks. Macroscopic prediction estimates the overall impact of information diffusion, while microscopic prediction focuses on identifying the next user to be influenced. While prior research often concentrates on one of these aspects, a few tackle both concurrently. These two tasks provide complementary insights into the diffusion process at different levels, revealing common traits and unique attributes. The exploration of leveraging common features across these tasks to enhance information prediction remains an underexplored avenue. In this paper, we propose an intuitive and effective model that addresses both macroscopic and microscopic prediction tasks. Our approach considers the interactions and dynamics among cascades at the macro level and incorporates the social homophily of users in social networks at the micro level. Additionally, we introduce adversarial training and orthogonality constraints to ensure the integrity of shared features. Experimental results on four datasets demonstrate that our model significantly outperforms state-of-the-art methods.

Network alignment involves identifying corresponding nodes across multiple networks. The majority of existing methods adhere to the assumption of consistency. However, due to distinct graph generation mechanisms, anchor nodes in real-world datasets often exhibit more intricate structural patterns, such as having multiple different neighbors and higher-order associations. Relying solely on consistency while disregarding the intricate patterns of anchor links may potentially inflict substantial detriment upon both the accuracy of network alignment and the generality of the model. In this paper, we introduce the disparity and diversity based on distinct structural patterns of ubiquitous anchor links. We propose a comprehensive framework that employs first-order proximity, lower-order discriminability, and higher-order correlation to model consistency, disparity, and diversity. We also incorporate a post-fusion mechanism for effectively integrating alignment matrices. Furthermore, we innovatively introduce hyperbolic space as an embedding space to further minimize embedding distortion. Extensive experiments have shown that our approach achieves state-of-the-art alignment results and yields notable improvements in the overall versatility of the model.

Generative self-supervised learning (SSL), especially masked autoencoders (MAE), has greatly succeeded and garnered substantial research interest in graph machine learning. However, the research of MAE in dynamic graphs is still scant. This gap is primarily due to the dynamic graph not only possessing topological structure information but also encapsulating temporal evolution dependency. Applying a random masking strategy which most MAE methods adopt to dynamic graphs will remove the crucial subgraph that guides the evolution of dynamic graphs, resulting in the loss of crucial spatio-temporal information in node representations. To bridge this gap, in this paper, we propose a novel Informative Subgraphs Aware Masked Auto-Encoder in Dynamic Graph, namely DyGIS. Specifically, we introduce a constrained probabilistic generative model to generate informative subgraphs that guide the evolution of dynamic graphs, successfully alleviating the issue of missing dynamic evolution subgraphs. The informative subgraph identified by DyGIS will serve as the input of dynamic graph masked autoencoder (DGMAE), effectively ensuring the integrity of the evolutionary spatio-temporal information within dynamic graphs. Extensive experiments on eleven datasets demonstrate that DyGIS achieves state-of-the-art performance across multiple tasks.

Thanks to the development of the Internet of Things, a large number of sensors have been deployed, resulting in the collection of abundant time series data. These data series contain potential space-time connection and noise at the same time. Prediction and health management (PHM) aim to provide decision support based on the health state of an entire engineering system. Additionally, the predicting future values also contribute to decision making and fall under the category of time series forecasting. While the existing methods focus on capturing the correlation between the data and reducing the impact of noise, they often fail to fully utilize the noise present in the time series data. In this article, we propose a framework for multivariate time series forecasting called GAGNN. This framework integrates the idea of a generative adversarial network and a graph neural network organically. It adopts the graph neural network as the generator and a multilayer perceptron as the discriminator. Finally, the prediction module is used to obtain the prediction results. The generator, discriminator, and prediction module are trained jointly. Our experimental results demonstrate that our model outperforms the original model on most benchmark data sets and achieves the best results on three out of six benchmark data sets.

Heterogeneous graphs (HGs) with multiple entity and relation types are common in real-world networks. Heterogeneous graph neural networks (HGNNs) have shown promise for learning HG representations. However, most HGNNs are designed for static HGs and are not compatible with heterogeneous temporal graphs (HTGs). A few existing works have focused on HTG representation learning but they care more about how to capture the dynamic evolutions and less about their compatibility with those well-designed static HGNNs. They also handle graph structure and temporal dependency learning separately, ignoring that HTG evolutions are influenced by both nodes and relationships. To address this, we propose HGN2T, a simple and general framework that makes static HGNNs compatible with HTGs. HGN2T is plug-and-play, enabling static HGNNs to leverage their graph structure learning strengths. To capture the relationship-influenced evolutions, we design a special mechanism coupling both the HGNN and sequential model. Finally, through joint optimization by both detection and prediction tasks, the learned representations can fully capture temporal dependencies from historical information. We conduct several empirical evaluation tasks, and the results show our HGN2T can adapt static HGNNs to HTGs and overperform existing methods for HTGs.

Federated Learning (FL) empowers multiple clients to collaboratively learn a global generalization model without the need to share their local data, thus reducing privacy risks and expanding the scope of AI applications. However, current works focus less on data in a highly nonidentically distributed manner such as graph data which are common in reality, and ignore the problem of model personalization between clients for graph data training in federated learning. In this paper, we propose a novel personality graph federated learning framework based on variational graph autoencoders that incorporates model contrastive learning and local fine-tuning to achieve personalized federated training on graph data for each client, which is called FedVGAE. Then we introduce an encoder-sharing strategy to the proposed framework that shares the parameters of the encoder layer to further improve personality performance. The node classification and link prediction experiments demonstrate that our method achieves better performance than other federated learning methods on most graph datasets in the non-iid setting. Finally, we conduct ablation experiments, the result demonstrates the effectiveness of our proposed method.

Network embedding is an important class of link prediction methods, which can use the distance between learned low-dimensional node representations to characterize the similarity between nodes. Traditional network embedding methods focus on single-layer networks, while in reality, a large part of complex networks are not isolated, but interdependent and interrelated, forming multiplex complex networks. Also, how to effectively exploit layer correlations in multiplex networks to learn more robust and valuable representations, to improve link prediction performance, has been a hot research topic in the field of complex network analysis. However, previous studies mainly focus on inferring intralinks in each layer of complex networks or anchor links among layers. Another issue that has not been discussed is how to predict potential links or reconstruct the network in unobserved relations based on existing multiplex networks. To this issue, we define a novel inductive link prediction problem in multiplex networks, in which most existing multichannel network embedding methods fail to solve. This is either because they only emphasize the specific structure information of an individual layer or only capture the common information for all layers. To effectively address this problem, we propose a novel embedding method termed interactive learning across relations (ILAR), to capture and fully exploit the multiple relations and complex layer correlations in multiplex networks. We leverage two convolutional modules and ILAR to capture the sufficient complementary and correlations in multiplex networks. Moreover, during interactive learning, a disparity constraint is introduced, which enforces the features encoded from two convolutional modules to be different and prevents information redundancy. Finally, the extensive experiments in several real-world datasets show that our model can significantly outperform the existing state-of-the-art network embedding methods on the novel link prediction problem in multiplex networks.

Roles are defined as the equivalent classes of isomorphic nodes in the network. They focus on the local connective patterns and describe the structural similarities between nodes, and learning role-based network embeddings can help to recognize identities or functions of entities in real-world networks. This field has been studied over the past decades, however, the existing role-based network embedding methods all concentrate too much on distinguishing node structures and ignore that nodes can belong to different roles even if they have the same local structures. Not only the classical network structure can influence the role of node, but also the emergence of different type of relationship between nodes has impact to it. We believe that roles are influenced by multiple independent factors, and nodes in the same roles should possess both similar local structures and entangled patterns with neighbors hidden in each factor, but most of the existing methods did not clearly point out this challenge. Therefore, we propose a disentangled framework based on graph neural networks to simultaneously model the local structures and interactive relationships in multiple factors to generate role-oriented network embeddings. We design a novel role-aware neighbor choosing mechanism to assign each neighbor a different interactive weight for each latent factor, which can measure its influence on roles. We conduct experiments on synthetic and real-world networks, and the results demonstrate the superiority and effectiveness of our model.

Change point detection in dynamic networks aims to detect the points of sudden change or abnormal events within the network. It has garnered substantial interest from researchers due to its potential to enhance the stability and reliability of real-world networks. Most change point detection methods are based on statistical characteristics and phased training, and some methods are required to set the percent of change points. Meanwhile, existing methods for change point detection suffer from two limitations. On one hand, they struggle to extract snapshot features that are crucial for accurate change point detection, thereby limiting their overall effectiveness. On the other hand, they are typically tailored for specific network types and lack the versatility to adapt to networks of varying scales. To solve these issues, we propose a novel unified end-to-end framework called Variational Graph Gaussian Mixture model (VGGM) for change point detection in dynamic networks. Specifically, VGGM combines Variational Graph Auto-Encoder (VGAE) and Gaussian Mixture Model (GMM) through joint training, incorporating a Mixture-of-Gaussians prior to model dynamic networks. This approach yields highly effective snapshot embeddings via VGAE and a dedicated readout function, while automating change point detection through GMM. The experimental results, conducted on both real-world and synthetic datasets, clearly demonstrate the superiority of our model in comparison to the current state-of-the-art methods for change point detection.

Due to numerous computation-intensive and delay-sensitive tasks in the Internet of Vehicles (IoV), Vehicular Edge Computing (VEC) is increasingly playing a crucial role as a key solution in the IoV. However, how to concurrently enhance communication quality and reduce the cost of latency and energy has emerged as a critical challenge in VEC. To tackle the above problem, we propose a Lyapunov-guided offloading based on the Soft Actor-Critic (SAC) algorithm, named LySAC, to minimize the average cost of the Integrated Sensing and Communications (ISAC) technology-aided IoV, where ISAC technology can effectively improve the communication quality by harnessing high-frequency waveforms to seamlessly integrate communication and sensing functionalities. First, we model the offloading process of ISAC-Aided IoV as an optimization problem of the joint cost of delay and energy with long-term energy consumption and queue stability. Then we formulate the optimization problem as a Lyapunov optimization and utilize the SAC method to find the optimal offloading decisions. Finally, we conduct extensive experiments and the results demonstrate the effectiveness and superiority of the proposed LySAC in minimizing total cost while maintaining queue stability and meeting long-term energy requirements compared with other several baseline schemes.

Capturing structural similarity has been a hot topic in the field of network embedding (NE) recently due to its great help in understanding node functions and behaviors. However, existing works have paid very much attention to learning structures on homogeneous networks, while the related study on heterogeneous networks is still void. In this article, we try to take the first step for representation learning on heterostructures, which is very challenging due to their highly diverse combinations of node types and underlying structures. To effectively distinguish diverse heterostructures, we first propose a theoretically guaranteed technique called heterogeneous anonymous walk (HAW) and give two more applicable variants. Then, we devise the HAW embedding (HAWE) and its variants in a data-driven manner to circumvent using an extremely large number of possible walks and train embeddings by predicting occurring walks in the neighborhood of each node. Finally, we design and apply extensive and illustrative experiments on synthetic and real-world networks to build a benchmark on heterostructure learning and evaluate the effectiveness of our methods. The results demonstrate our methods achieve outstanding performance compared with both homogeneous and heterogeneous classic methods and can be applied on large-scale networks.

Cardiotocography (CTG) is an important medical diagnostic tool when it comes to monitoring fetal wellbeing. It records Fetal Heart Rate (FHR) and uterine contraction activity, and can be used to detect whether the fetus is receiving oxygen adequately or in distress. Unfortunately, the interpretation of CTG recordings is highly subjective which can lead to unnecessary medical intervention that represents a risk for both the mother and the fetus. In this regard, intelligent CTG (ICTG) classification is a challenging research that can assist obstetricians in making clinical decisions, thereby improving the efficiency and accuracy of pregnancy management. But, many of these models focus on one specific modality that lack generalization to unseen or test data samples. In this study, a multi-modal fusion learning approach is proposed for pathological diagnosis of fetal distress. It combines signal and image modalities for multi-modal inputs and develops a Multi-modal Encoder Network (MENet) model based on DNN for capturing the underlying distribution of multi-modal data samples. Experimental results demonstrate that under the constraints of same classifier structure, MENet performs well in terms of classification accuracy and stability, far superior to several existing ICTG algorithms.

Recently, network embedding (NE) is an amazing research point in complex networks and devoted to a variety of tasks. Nearly, all the methods and models of NE are based on the local, high-order, or global similarity of the networks, and few studies have focused on the role discovery or structural similarity, which is of great significance in spreading dynamics and network theory. Meanwhile, existing NE models for role discovery suffer from two limitations, that is: 1) they fail to model the varying dependencies between each node and its neighbor nodes and 2) they cannot capture the effective node features which are helpful to role discovery, which makes these methods ineffective when applied to the role discovery task. To solve the above problems of NE for role discovery or structural similarity, we propose a unified deep learning framework, called RDAA, which can effectively represent features of nodes and benefit the Role Discovery-guided NE with a deep autoencoder, while modeling the local links with an Attention mechanism. In addition, we design an elaborately binding technique to combine both parts and optimize the framework in a unified way. We conduct different experiments, including visualization, role classification, role discovery, and running time compared to popular NE methods for both proximity and structural similarity. The RDAA has better performance on all the datasets and achieves good tradeoffs.

Temporal community detection is helpful to discover and analyze significant groups or clusters hidden in dynamic networks in the real world. A variety of methods, such as modularity optimization, spectral method, and statistical network model, has been developed from diversified perspectives. Recently, network embedding-based technologies have made significant progress, and one can exploit deep learning superiority to network tasks. Although some methods for static networks have shown promising results in boosting community detection by integrating community embedding, they are not suitable for temporal networks and unable to capture their dynamics. Furthermore, the dynamic embedding methods only model network varying without considering community structures. Hence, in this article, we propose a novel unsupervised dynamic community detection model, which is based on network embedding and can effectively discover temporal communities and model dynamic networks. More specifically, we propose the community prior by introducing the Gaussian mixture model (GMM) in the variational autoencoder, which can obtain community information and better model the evolutionary characteristics of community structure and node embedding by utilizing the variant of gated recurrent unit (GRU). Extensive experiments conducted in real-world and artificial networks demonstrate that our proposed model has a better effect on improving the accuracy of dynamic community detection.

Anomaly detection in dynamic networks aims to find network elements (e.g., nodes, edges, subgraphs, change points) with significantly different behaviors from the vast majority, it can also devote to community detection and evolution and prediction tasks. Most existing methods focus on one specific task, that is, only detect anomalies of one type of element isolated, so they lose the ability to model the correlation and driving mechanism between different abnormal behavior. Considering that the anomaly detection of one type of element is helpful to other types of elements, i.e., the temporal evolution hidden the dynamic networks are driven by indivisible behavior patterns. So in this paper, we propose a unified Generation model to analyze the dynamic network for Exploring the Abnormal Behaviors of different Scales (GEABS). It can model the relation and catch different levels (node, community and network) of anomaly with a joint statistical network model and detect the community structure and its evolution. Specifically, we denote the parameters of node popularity, community membership to generate the dynamic network with stochastic block model (SBM), we also describe the varying of node and community by dynamic process. With a well-designed generative mechanism, it can detect the change point on network level, temporal evolution on community level and abnormal behavior on node level synchronously, besides, it also detects the community structure effectively. We also propose an effective optimization algorithm with variational inference. Experimental results show that the GEABS achieves better performance on abnormal behavior and community structure compared with baselines.

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

A variety of methods have been proposed for modeling and mining dynamic complex networks, in which the topological structure varies with time. As the most popular and successful network model, the stochastic block model (SBM) has been extended and applied to community detection, link prediction, anomaly detection, and evolution analysis of dynamic networks. However, all current models based on the SBM for modeling dynamic networks are designed at the community level, assuming that nodes in each community have the same dynamic behavior, which usually results in poor performance on temporal community detection and loses the modeling of node abnormal behavior. To solve the above-mentioned problem, this article proposes a hierarchical Bayesian dynamic SBM (HB-DSBM) for modeling the node-level and community-level dynamic behavior in a dynamic network synchronously. Based on the SBM, we introduce a hierarchical Dirichlet generative mechanism to associate the global community evolution with the microscopic transition behavior of nodes near-perfectly and generate the observed links across the dynamic networks. Meanwhile, an effective variational inference algorithm is developed and we can easy to infer the communities and dynamic behaviors of the nodes. Furthermore, with the two-level evolution behaviors, it can identify nodes or communities with abnormal behavior. Experiments on simulated and real-world networks demonstrate that HB-DSBM has achieved state-of-the-art performance on community detection and evolution. In addition, abnormal evolutionary behavior and events on dynamic networks can be effectively identified by our model.

Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modelling into the framework of GCN so that it can realize “block-guided classified aggregation”, and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modelling into the aggregation process, GCN is able to automatically aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets.

Exploring the differences and important patterns of nodes from the perspective of roles has gradually developed into an interesting and important topic in network analysis. However, existing role-oriented network embedding methods focus more on identifying underlying roles for static network, which leads to complex temporal behaviors being overlooked and degraded performance facing dynamic network. The few role analytics methods for dynamic networks either cannot learn general node representations or fail to discovery role transitions of nodes. In this work, we propose a unified framework RDNE (Role-oriented Dynamic Network Embedding) to tackle such challenges, which aim to learn multiple embeddings for individual nodes based on time-varying structural behaviors. Based on regular equivalence, RDNE propagates the structural features over the graph to derive the initial role-oriented representations. Then, it applies capsule network to further model the mapping between nodes and roles, which is the first time capsule network is used for role discovery. For the varying and temporal dependence within dynamic network, we utilize the Gated Recurrent Unit to compute historical information and use historical information to influence the generation of representations at the next snapshot. Comprehensive experiments on both synthetic and real-world networks validate the superiority of the proposed RDNE.

In Community Question Answering (CQA) websites, expert finding aims at seeking suitable experts to answer questions. The key is to explore the inherent relevance based on the representations of questions and experts. Existing methods usually learn these features from single view information (e.g., question title), which would be not insufficient to fully learn their representations. In this paper, we propose a personalized expert finding method with a multi-view attentive matching mechanism. We design three modules under the multi-view paradigm, including a question encoder, an intra-view encoder, and an inter-view encoder, which aims to comprehend the comprehensive relationships between experts and questions. In the question encoder, we learn the multi-view question features from its title, body and tag views respectively. In the intra-view encoder, we design an interactive attention network to capture the view-specific relevance between the target question and the historical answered questions of experts for all different views. Furthermore, in the inter-view encoder we employ a personalized attention network to aggregate different view information to learn expert/question representations. In this way, the match of the expert and question could be fully captured from the multi-view information via the intra- and inter-view mechanisms. Experimental results on six datasets demonstrate that the proposed method could achieve better performance than existing state-of-the-art methods.

Recently, Network Embedding (NE) has become one of the most attractive research topics in machine learning and data mining. NE approaches have achieved promising performance in various graph mining tasks including link prediction and node clustering and classification. A wide variety of NE methods focus on the proximity of networks, they learn community-oriented embedding for each node, where the corresponding representations are similar if two nodes are closer to each other in the network. Meanwhile, there is another type of structural similarity, i.e., role-based similarity, which is completely different from and complementary to the proximity. In order to preserve the role-based structural similarity, the problem of role-oriented NE is raised. However, compared to the community-oriented NE, there are only a few role-oriented embedding approaches proposed recently. Although less explored, considering the importance of roles in analyzing networks and many applications that role-oriented NE can shed light on, it is necessary and timely to provide a comprehensive overview of existing role-oriented NE methods. In this review, we first clarify the differences between community-oriented and role-oriented network embedding. Afterward, we propose a general framework for understanding role-oriented NE and a two-level categorization to better classify existing methods. Then, we select some representative methods according to the proposed categorization and briefly introduce them by discussing their motivation, development, and differences. Moreover, we conduct comprehensive experiments to empirically evaluate these methods on a variety of role-related tasks including node classification and clustering (role discovery), top-k similarity search, and visualization using some widely used synthetic and real-world datasets. Finally, we further discuss the research trend of role-oriented NE from the perspective of applications and point out some potential future directions.

In order to meet people’s demands for intelligent and user-friendly Internet of Things (IoT) services, the amount of computation is increasing rapidly and the requirements of task delay are becoming increasingly more stringent. However, the constrained battery capacity of IoT devices greatly limits the user experience. Energy harvesting technologies enable green energy to provide continuous energy support for devices in the IoT environment. Together with the maturity of the mobile edge computing technology and the development of parallel computing, it provides a strong guarantee for the normal operation of resource-constrained IoT devices. In this article, we design a parallel offloading strategy based on Lyapunov optimization, which is conducive to efficiently finding the optimal decision for delay-sensitive and compute-intensive tasks. We establish a stochastic optimization problem on a discrete-time slot system and propose a green parallel online offloading algorithm (GPOOA). By decoupling the target problem three times, the joint optimization of green energy, task division factor, CPU frequency, and transmission power is realized. Experimental results demonstrate that under the constraints of strict task deadlines and limited server computing resources, GPOOA performs well in terms of system cost and task drop ratio, far superior to several existing offloading algorithms.

Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal network embedding (TNE) methods are facing three challenges: 1) it cannot describe the temporal dependence across network snapshots; 2) the node embedding in the latent space fails to indicate changes in the network topology; and 3) it cannot avoid a lot of redundant computation via parameter inheritance on a series of snapshots. To overcome these problems, we propose a novel TNE method named temporal network embedding method based on the VAE framework (TVAE), which is based on a variational autoencoder (VAE) to capture the evolution of temporal networks for link prediction. It not only generates low-dimensional embedding vectors for nodes but also preserves the dynamic nonlinear features of temporal networks. Through the combination of a self-attention mechanism and recurrent neural networks, TVAE can update node representations and keep the temporal dependence of vectors over time. We utilize parameter inheritance to keep the new embedding close to the previous one, rather than explicitly using regularization, and thus, it is effective for large-scale networks. We evaluate our model and several baselines on synthetic data sets and real-world networks. The experimental results demonstrate that TVAE has superior performance and lower time cost compared with the baselines.

Community detection is a research hotspot in machine learning and data mining. However, most of the existing community detection methods only rely on the lower-order connectivity patterns, while ignoring the higher-order connectivity patterns, and unable to capture the building blocks of the complex network. In recent years, some community detection methods based on higher-order structures have been developed, but they mainly focus on the motif network composed of higher-order structures, which violate the original lower-order topological structure and are affected by the fragmentation issue, resulting in the deviation of community detection results. Therefore, there is still a lack of community detection methods that can effectively utilize higher-order connectivity patterns and lower-order connectivity patterns. To overcome the above limitations, this paper proposes the Hybrid-order Stochastic Block Model (HSBM) from the perspective of the generative model. Based on the classical stochastic block model, the generation of lower-order structure and higher-order structure of the network is modeled uniformly, and the original topological properties of the network are maintained while using higher-order connectivity patterns. At the same time, a heuristic algorithm for community detection is proposed to optimize the objective function. Extensive experiments on six real-world datasets show that the proposed method outperforms the existing approaches.

Roles of nodes are defined as classes of equivalent nodes. Nodes that have similar local connective patterns may share the same role. As a complementary concept of community, role can also help to recognize real-world entities. For example, it can denote identity or function in social networks. Role has been studied over the past decades, and learning role-based network representations is crucial to many downstream tasks. The important step for role-based network embedding method is extracting features to measure structural similarity instead of proximity. Although some methods have been developed to capture role features to learn structural similarities between nodes, they all design these features of fixed types, such as the global, local, and higher-order features. These features can only represent a certain type of structure, and it is very difficult to model the complex relationship between different scale features in the field of role-based network embedding. Therefore, we propose a novel role-oriented network embedding framework based on adversarial learning between higher-order and local features (ARHOL) to generate powerful role-based node representations. The higher-order features are discrete so we leverage the Auto-Encoder on them to obtain continuous representations. Then we apply the GIN on its outputs to aggregate local information. Finally, we consider the GIN as the generator and design an adversarial game between local features and GIN outputs to integrate these two aspects of features, which can enhance each other and improve the robustness. The extensive experiments on real-world networks demonstrate the superiority and efficiency of our model, and prove the effectiveness of integrating higher-order and local features.

The dependencies across different layers are an important property in multiplex networks and a few methods have been proposed to learn the dependencies in various ways. When capturing the dependencies across different layers, some of them assumed the structure among layers following consistent connectivity to force two nodes with a link in one layer tend to have links in other layers, some introduced a common vector to model the shared information across all layers. However, the correlations among layers in multiplex networks are diverse, which go beyond the connectivity consistency. In this paper, we propose a novel Modeling Correlations for Multiplex network Embedding (MCME) framework to learn the robust node representations for each layer. It can deal with complex correlations with a common structure, layer similarity and node heterogeneity through a unified framework in multiplex networks. To evaluate our proposed model, we conduct extensive experiments on several real-world datasets and the results demonstrate that our proposed model consistently outperforms state-of-the-art methods.

Role of node is defined on structural similarity or local connective pattern, describing the functions of node in the network. In real-world situation, it can denote person’s identity and status. It has been studied over the past decades, and learning role-based network representations is crucial to many downstream tasks. In this field, the important step for is extracting some measurements to evaluate structural similarity. Although some methods have been developed to capture the role features to learn the structural similarities between nodes, they all design the features of fixed types, such as global, local, and higher-order features. These features can only discover single type of roles, and simply combing them may cause damage to performance. It is very difficult to model the complex relationship between different scale features in the field of role-based network embedding. Therefore, we propose a novel adversarial framework to generate structural node representations via higher-order features and adversarial learning (SHOAL). We leverage the Auto-Encoder on higher-order features and some GNNs on its outputs to aggregate local neighbors. We believe that higher-order and local features can denote roles, and effectively integrating them will help for role discovery. So we consider the GNNs as the generator and design an adversarial game between these features, which can also improve the robustness. The experiments on real-world networks demonstrate the superiority and efficiency of our model, and the results also prove the effectiveness of integrating higher-order and local features.

Role-based network embedding methods aim to preserve node-centric connectivity patterns, which are expressions of node roles, into low-dimensional vectors. However, almost all the existing methods are designed for capturing a relaxation of automorphic equivalence or regular equivalence. They may be good at structure identification but could show poorer performance on role identification. Because automorphic equivalence and regular equivalence strictly tie the role of a node to the identities of all its neighbors. To mitigate this problem, we construct a framework called Curvature-based Network Embedding with Stochastic Equivalence (CNESE) to embed stochastic equivalence. More specifically, we estimate the role distribution of nodes based on discrete Ricci curvature for its excellent ability to concisely representing local topology. We use a Variational Auto-Encoder to generate embeddings while a degree-guided regularizer and a contrastive learning regularizer are leveraged to improving both its robustness and discrimination ability. The effectiveness of our proposed CNESE is demonstrated by extensive experiments on real-world networks.

The vast majority of community detection algorithms assume that the networks are totally observed. However, in reality many networks cannot be fully observed. On such network is edges-missing network, where some relationships (edges) between two entities are missing. Recently, several works have been proposed to solve this problem by combining link prediction and community detection in a two-stage method or in a unified framework. However, the goal of link prediction, which is to predict as many correct edges as possible, is not consistent with the requirement for predicting the important edges for discovering community structure on edges-missing networks. Thus, combining link prediction and community detection cannot work very well in terms of detecting community structure for edges-missing network. In this paper, we propose a community self-guided generative model which jointly completes the edges-missing network and identifies communities. In our new model, completing missing edges and identifying communities are not isolated but closely intertwined. Furthermore, we developed an effective model inference method that combines a nested Expectation-Maximization (EM) algorithm and Metropolis-Hastings Sampling. Extensive experiments on real-world edges-missing networks show that our model can effectively detect community structures while completing missing edges.

Review summarization aims to generate condensed text for online product reviews, and has attracted more and more attention in E-commerce platforms. In addition to the input review, the quality of generated summaries is highly related to the characteristics of users and products, e.g., their historical summaries, which could provide useful clues for the target summary generation. However, most previous works ignore the underlying interaction between the given input review and the corresponding historical summaries. Therefore, we aim to explore how to effectively incorporate the history information into the summary generation. In this paper, we propose a novel transformer-based reasoning framework for personalized review summarization. We design an elaborately adapted transformer network containing an encoder and a decoder, to fully infer the important and informative parts among the historical summaries in terms of the input review to generate more comprehensive summaries. In the encoder of our approach, we develop an inter- and intra-attention to involve the history information selectively to learn the personalized representation of the input review. In the decoder part, we propose to incorporate the constructed reasoning memory learning from historical summaries into the original transformer decoder, and design a memory-decoder attention module to retrieve more useful information for the final summary generation. Extensive experiments are conducted and the results show our approach could generate more reasonable summaries for recommendation, and outperform many competitive baseline methods.

With the proliferation of compute-intensive and delay-sensitive mobile applications, large amounts of computational resources with stringent latency requirements are required on Internet-of-Things (IoT) devices. One promising solution is to offload complex computing tasks from IoT devices either to mobile-edge computing (MEC) or mobile cloud computing (MCC) servers. MEC servers are much closer to IoT devices and thus have lower latency, while MCC servers can provide flexible and scalable computing capability to support complicated applications. To address the tradeoff between limited computing capacity and high latency, and meanwhile, ensure the data integrity during the offloading process, we consider a blockchain scenario where edge computing and cloud computing can collaborate toward secure task offloading. We further propose a blockchain-enabled IoT-Edge-Cloud computing architecture that benefits both from MCC and MEC, where MEC servers offer lower latency computing services, while MCC servers provide stronger computation power. Moreover, we develop an energy-efficient dynamic task offloading (EEDTO) algorithm by choosing the optimal computing place in an online way, either on the IoT device, the MEC server or the MCC server with the goal of jointly minimizing the energy consumption and task response time. The Lyapunov optimization technique is applied to control computation and communication costs incurred by different types of applications and the dynamic changes of wireless environments. During the optimization, the best computing location for each task is chosen adaptively without requiring future system information as prior knowledge. Compared with previous offloading schemes with/without MEC and MCC cooperation, EEDTO can achieve energy-efficient offloading decisions with relatively lower computational complexity.

With the explosive growth of mobile data and the unprecedented demand for computing power, resource-constrained edge devices cannot effectively meet the requirements of Internet of Things (IoT) applications and Deep Neural Network (DNN) computing. As a distributed computing paradigm, edge offloading that migrates complex tasks from IoT devices to edge-cloud servers can break through the resource limitation of IoT devices, reduce the computing burden and improve the efficiency of task processing. However, the problem of optimal offloading decision-making is NP-hard, traditional optimization methods are difficult to achieve results efficiently. Besides, there are still some shortcomings in existing deep learning methods, e.g., the slow learning speed and the weak adaptability to new environments. To tackle these challenges, we propose a Deep Meta Reinforcement Learning-based Offloading (DMRO) algorithm, which combines multiple parallel DNNs with Q-learning to make fine-grained offloading decisions. By aggregating the perceptive ability of deep learning, the decision-making ability of reinforcement learning, and the rapid environment learning ability of meta-learning, it is possible to quickly and flexibly obtain the optimal offloading strategy from a dynamic environment. We evaluate the effectiveness of DMRO through several simulation experiments, which demonstrate that when compared with traditional Deep Reinforcement Learning (DRL) algorithms, the offloading effect of DMRO can be improved by 17.6%. In addition, the model has strong portability when making real-time offloading decisions, and can fast adapt to a new MEC task environment.

Product reviews can provide rich information about the opinions users have of products. However, it is nontrivial to effectively infer user preference and item characteristics from reviews due to the complicated semantic understanding. Existing methods usually learn features for users and items from reviews in single static fashions and cannot fully capture user preference and item features. In this article, we propose a neural review-based recommendation approach that aims to learn comprehensive representations of users/items under a three-tier attention framework. We design a review encoder to learn review features from words via a word-level attention, an aspect encoder to learn aspect features via a review-level attention, and a user/item encoder to learn the final representations of users/items via an aspect-level attention. In word- and review-level attentions, we adopt the context-aware mechanism to indicate importance of words and reviews dynamically instead of static attention weights. In addition, the attentions in the word and review levels are of multiple paradigms to learn multiple features effectively, which could indicate the diversity of user/item features. Furthermore, we propose a personalized aspect-level attention module in user/item encoder to learn the final comprehensive features. Extensive experiments are conducted and the results in rating prediction validate the effectiveness of our method.

Network embedding (NE), aiming to embed a network into a low dimensional latent representation while preserving the inherent structural properties of the network, has attracted considerable attention recently. Variational Autoencoder (VAE) has been widely studied for NE. Existing VAE based methods let the network follow a unimodal distribution, that is, they typically use some fixed distribution as the prior, e.g. Gaussian distribution. However, in reality networks often contain many complicated structural properties [5], [6] (such as the first/second order proximity, the motif or community structures, power-law, etc). The latent representation from unimodal and fixed distribution is not capable of describing such multi-modal characteristic of networks. To address this issue, we develop a new VAE method for NE, named Normalizing Flow Variational Graph Autoencoder (NF-VGA). We design a prior-generative module based on normalizing flows to generate flexible, multi-modal distribution as the prior of the latent representation. To make the generated prior better describe the coupling relationship between nodes, we further utilize network local structures to guide the prior generation. Extensive experiments on some real-world networks show a superior performance of the new approach over some state-of-the-art methods on some popular network embedding tasks.

Modeling how information diffuses across social network platforms can be widely used. Recently, researchers have used deep learning methods to model information cascades and forecast their progression without dependence on the hypothesis of the underlying diffusion model. Most of these studies use sequential models (e.g., recurrent neural networks, RNNs) and model cascades of information spread without using the network structure information. However, the network structure information substantially affects information spread, cross-dependence should be considered in cascade modeling, and recurrent neural networks produce poor results on long sequence modeling. To solve these issues, in this paper, we present a new cascade modeling method with the multihead self-attention mechanism. We design an encoder that combines network structure information with multihead self-attention to learn the representations of cascades and consider diverse user dependencies on the network. Experiments are conducted on both synthetic and real-world datasets. The results show that the proposed method performs better on the long sequence cascade prediction than the state-of-the-art methods.

There are two main paradigms to exploit review information for recommendation. One is to concatenate all reviews of a user/item into a long document, which may neglect the different usefulness of reviews. The other paradigm is review-level i.e., analyzing each review separately to learn user/item features. In fact, the two paradigms are complementary, and fusing them together has the potential to learn more comprehensive features of users/items. Hence, we propose a unified framework to jointly learn document- and review-level representations of users/items. We design a document encoder to learn document-level features of users/items. Then, we use a review encoder to learn representations of reviews from words, and a user/item encoder to learn review-level features of users/items. Besides, different reviews from the same user may have different importance for different target items due to different item characteristics. We propose a cross attention model for user representation learning whose query vector is the embedding of target item ID, and apply it to the above three encoders to select different informative words and reviews for different target items. Extensive experiments validate the effectiveness of our method.

Overlapping community detection has triggered recent research in network analysis. One of the promising techniques for finding overlapping communities is the popular stochastic models, which, unfortunately, have some common drawbacks. They do not support an important observation that highly connected nodes are more likely to reside in the overlapping regions of communities in the network. These methods are in essence not truly unsupervised, since they require a threshold on probabilistic memberships to derive overlapping structures and need the number of communities to be specified a priori . We develop a new method to address these issues for overlapping community detection. We first present a stochastic model to accommodate the relative importance and the expected degree of every node in each community. We then infer every overlapping community by ranking the nodes according to their importance. Second, we determine the number of communities under the Bayesian framework. We evaluate our method and compare it with five state-of-the-art methods. The results demonstrate the superior performance of our method. We also apply this new method to two applications, showing its superb performance on practical problems.

Finding semantic communities using network topology and contents together is a hot topic in community detection. Existing methods often use word attributes in an indiscriminate way to help finding communities. Through analysis we find that, words in networked contents often embody a hierarchical semantic structure. Some words reflect a background topic of the whole network with all communities, some imply the high-level general topic covering several topic-related communities, and some imply the high-resolution specialized topic to describe each community. Ignoring such semantic structures often leads to defects in depicting networked contents where deep semantics are not fully utilized. To solve this problem, we propose a new Bayesian probabilistic model. By distinguishing words from either a background topic or some two-level topics (i.e., general and specialized topics), this model not only better utilizes the networked contents to help finding communities, but also provides a clearer multiplex semantic community interpretation. We then give an efficient variational algorithm for model inference. The superiority of this new approach is demonstrated by comparing with ten state-of-the-art methods on nine real networks and an artificial benchmark. A case study is further provided to show its strong ability in deep semantic interpretation of communities.

The purpose of network embedding is to learn a low-dimensional representation for each node in the network. One can then use this low-dimensional representation to solve some network analysis tasks, such as node classification and node clustering. At present, there are several network embedding learning methods based on GAN (Generative Adversarial Networks) to enhance the robustness of representations. However, these methods have two drawbacks. First, they are often too difficult to be trained stably. Second, they only learn the robust representations by matching the posterior distribution of the latent representations to the given priors. On the contrary, Capsule Networks can learn a more equivariant representation of images that is more robust to the changes in pose and spatial relationships of parts of objects in images. However, there is still no research using Capsule Network for network embedding since the social network is essentially different from images. For this problem, we propose a new approach of adversarial capsule learning (ACL) for network embedding, which is the first time to use Capsule Network in the network analysis tasks. To be specific, the new model consists of two parts, a generator and discriminator. We use Graph Convolutional Networks (GCN) as the generator to learn the embedding of nodes, and use Capsule Network as the discriminator to distinguish between the real and fake samples as accurately as possible. The experimental results demonstrate the effectiveness of the proposed new method.

Network embedding (NE) maps a network into a low-dimensional space while preserving intrinsic features of the network. Variational Auto-Encoder (VAE) has been actively studied for NE. These VAE-based methods typically utilize both network topologies and node semantics and treat these two types of data in the same way. However, the information of network topology and information of node semantics are orthogonal and are often from different sources; the former quantifies coupling relationships among nodes, whereas the latter represents node specific properties. Ignoring this difference affects NE. To address this issue, we develop a network-specific VAE for NE, named as NetVAE. In the encoding phase of our new approach, compression of network structures and compression of node attributes share the same encoder in order to perform co-training to achieve transfer learning and information integration. In the decoding phase, a dual decoder is introduced to reconstruct network topologies and node attributes separately. Specifically, as a part of the dual decoder, we develop a novel method based on a Gaussian mixture model and the block model to reconstruct network structures. Extensive experiments on large real-world networks demonstrate a superior performance of the new approach over the state-of-the-art methods.

Existing review-based recommendation methods usually use the same model to learn the representations of all users/items from reviews posted by users towards items. However, different users have different preference and different items have different characteristics. Thus, the same word or the similar reviews may have different informativeness for different users and items. In this paper we propose a neural recommendation approach with personalized attention to learn personalized representations of users and items from reviews. We use a review encoder to learn representations of reviews from words, and a user/item encoder to learn representations of users or items from reviews. We propose a personalized attention model, and apply it to both review and user/item encoders to select different important words and reviews for different users/items. Experiments on five datasets validate our approach can effectively improve the performance of neural recommendation.

Topic models have many important applications in fields such as Natural Language Processing. Topic embedding modelling aims at introducing word and topic embeddings into topic models to describe correlations between topics. Existing topic embedding methods use documents alone, which suffer from the topical fuzziness problem brought by the introduction of embeddings of semantic fuzzy words, e.g. polysemous words or some misleading academic terms. Links often exist between documents which form document networks. The use of links may alleviate this semantic fuzziness, but they are sparse and noisy which may meanwhile mislead topics. In this paper, we utilize community structure to solve these problems. It can not only alleviate the topical fuzziness of topic embeddings since communities are often believed to be topic related, but also can overcome the drawbacks brought by the sparsity and noise of networks (because community is a high-order network information). We give a new generative topic embedding model which incorporates documents (with topics) and network (with communities) together, and uses probability transition to describe the relationship between topics and communities to make it robust when topics and communities do not match. An efficient variational inference algorithm is then proposed to learn the model. We validate the superiority of our new approach on two tasks, document classifications and visualization of topic embeddings, respectively.

Using network topology and semantic contents to find topic-related communities is a new trend in the field of community detection. By analyzing texts in social networks, we find that topics in networked contents are often hierarchical. In most cases, they have a two-level semantic structure with general and specialized topics, to respectively denote common and specific interests of communities. However, the existing community detection methods ignore such a hierarchy and take all words used to describe node semantics from an identical perspective. This indiscriminate use of words leads to natural defects in depicting networked content in which the deep semantics is not fully utilized. To address this problem, we propose a novel probabilistic generative model. By distinguishing the general and specialized topics of words, our model not only can find community structures more accurately, but also provide two-level semantic interpretation for each community. We train the model by deriving an efficient inference method under the framework of variational expectation-maximization. We provide a case study to show the ability of our algorithm in deep semantic interpretability of communities. The superiority of our algorithm for community detection is further demonstrated in comparison with eight state-of-the-art algorithms on eight real-world networks.

Temporal networks are increasingly prevalent in modern data, and the analysis of such networks can uncover the important phenomenon and characterize the properties of networks of dynamical units. This paper presents a new community detection model using nonnegative matrix factorization (NMF) which is capable of detecting and tracking dynamic communities in temporal networks. A novel temporal smoothness constraint by preserving the expected node popularity of two consecutive timeslices is proposed, and the community membership transition matrices are introduced to capture the sudden changes in network topologies in dynamic cases. We then propose a gradient descent algorithm to optimize objective function and prove its correctness and convergence. Experimental results on some synthetic and real benchmarked networks show the effectiveness of the proposed new method in detecting communities as well as finding their changes in dynamic networks.