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.

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.

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.

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.

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.

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.

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.

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.

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.

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.