Graph-based fraud detection (GFD) aims to identify fraud nodes within graph-structured data that significantly deviate from the majority of benign nodes. However, existing graph neural networks (GNNs) often struggle in GFD scenarios due to their reliance on homophily assumption, which is frequently violated by the inherent homophily-heterophily mixture of fraud graphs. Moreover, most methods focus primarily on local topology, overlooking mesoscopic community structures, making them less efficient in detecting suspicious patterns like densely connected subgraphs. To address the aforementioned issues, we present NeCo, a novel approach that integrates mixture of neighborhood and community experts for graph-based fraud detection. Specifically, we first introduce a fraud-discriminative representation preservation mechanism from a neighborhood perspective, leveraging the empirical finding that fraud nodes tend to exhibit larger feature propagation discrepancies compared to benign nodes. We then design a community-oriented node representation module that models structural compactness among nodes, enabling the detection of suspicious topological patterns associated with fraud behaviors. By integrating these two complementary perspectives, NeCo can effectively captures both local inconsistency and global structural irregularity. Extensive experiments across five real-world datasets demonstrate the effectiveness of our proposed NeCo over state-of-the-art baselines.

The cold-start recommendation has been challenging due to the limited historical interactions for new users and new items. Recently, methods based on meta-learning and graph neural networks are effective on this problem. However, these methods mainly focus on the missing user–item interactions in cold-start scenarios, overlooking the missing of user/item feature information, which significantly limits the quality and effectiveness of node embeddings. To address this problem, we propose an innovative Large Language Model-Guided Feature-Structure Augmented Graph Neural Network (LLM-FSGNN). The proposed framework integrates external semantic knowledge with internal graph structures via LLMs. It generates more comprehensive and robust user and item node representations. Specifically, we leverage the semantic reasoning capabilities of LLMs to extract textual descriptions of users and items, constructing a semantic view to enhance ambiguous or missing attributes and enrich node feature representations. Simultaneously, by analyzing item content to better understand user preferences, LLMs can accurately predict users’ potential intentions toward items and uncover latent interaction relationships, thus strengthening structural features. In addition, we introduce a graph structure enhancement module to complement structural relations from a graph-based perspective, mitigating hallucination issues in LLMs. Experimental results on multiple public benchmark datasets demonstrate consistent improvements in cold-start scenarios. For example, LLM-FSGNN achieves 4.8% lower MAE on MovieLens100K, 3.6% lower MAE on MovieLens1M, and 4.2% lower MAE on Amazon compared with the current state-of-the-art methods.

In graph anomaly detection (GAD), the fact that anomalous nodes usually exhibit high heterophily, while most Graph Neural Networks (GNNs) have homophily assumptions, leads to poor performance. Many studies have attempted to solve this problem by employing a set of graph filters covering various frequencies. Their ultimate goal is to design the most appropriate spectral filter to capture the complex signals generated by normals and anomalies. The critical aspect lies in the fusion of information from filters with different frequency response functions. However, existing methods lack a clear indicator to guide the fusion of information at different frequencies. In this paper, we find that local homophily is a valuable metric for assessing the weights of high- and low-frequency information at the node level, and explicitly point out that the accuracy of local homophily is positively correlated with the accuracy of anomaly detection. Moreover, we unveil the phenomenon of camouflage in anomalous, wherein these nodes disguise themselves by making their features resemble those of surrounding normals.

Graph Neural Networks (GNNs), which obtain node embeddings by attribute propagates along graph topology, exhibit significant power in graph-structured data mining. However, graphs in the real world are usually text-rich, where the text can not only be represented as node attributes, but also contains valuable objective semantic structures. Moreover, the graph topology also exhibits complex subjective semantic structures, especially the heterophily where nodes from different classes are prone to build connections, making existing GNNs that work under the assumption of homophily incapable to realize generalization. To tackle aforementioned limitations, we design a new text-rich graph neural network from a unified perspective, namely SO-GNN. It can effectively enhance the expressive power of GNNs by modeling the implicit but informative subjective-objective semantics underlying the text-rich graphs. Specifically, we first introduce a new constrained Markov matrix with well-defined probabilistic diffusion dynamics to guide information propagation, where the neighbors are more appropriate and indicative in providing both local and global subjective semantics. We then construct a flexible heterogeneous text graph to gain a deeper insight into objective semantics, providing indispensable information for learning node embedding. Finally, we unite subjective and objective semantics in an end-to-end manner, so that the model can fully utilize the most relevant information for downstream tasks. Extensive experiments across various text-rich graphs with low-to-high homophily demonstrate the effectiveness and flexibility of the proposed SO-GNN over state-of-the-arts.

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

Heterogeneous information network (HIN) embedding, aiming to map the structure and semantic information in a HIN to distributed representations, has drawn considerable research attention. Graph neural networks for HIN embeddings typically adopt a hierarchical attention (including node-level and meta-path-level attentions) to capture the information from meta-path-based neighbors. However, this complicated attention structure often cannot achieve the function of selecting meta-paths due to severe overfitting. Moreover, when propagating information, these methods do not distinguish direct (one-hop) meta-paths from indirect (multi-hop) ones. But from the perspective of network science, direct relationships are often believed to be more essential, which can only be used to model direct information propagation. To address these limitations, we propose a novel neural network method viaimplicitlyutilizing attention and meta-paths, which can relieve the severe overfitting brought by the current over-parameterized attention mechanisms on HIN. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer, along with stacking the information propagation of direct linked meta-paths layer-by-layer, realizing the function of attentions for selecting meta-paths in an indirect way. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation. That is, we first model the whole propagation process with well-defined probabilistic diffusion dynamics, and then introduce a random graph-based constraint which allows it to reduce noise with the increase of layers. Extensive experiments demonstrate the superiority of the new approach over state-of-the-art methods.

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.

Graph neural network (GNN) has become a popular tool to analyze the graph data. Existing GNNs only focus on networks with first-order dependency, that is, conventional networks following the Markov property. However, many networks in real life own the higher-order dependency, such as click-stream data where the choice of the next page depends not only on the current page but also on previous pages. This kind of sequential data from complex systems (including natural dependencies) are often ignored by existing GNNs which makes them ineffective. To address this problem, we propose for the first time new GNN approaches for higher-order networks in this paper. First, we form sequence fragments by the current node and its predecessor nodes of different orders as candidate higher-order dependencies. When the fragment significantly affects the probability distribution of different successor nodes of the current node, we include it in the higher-order dependency set. We formulize the network with higher-order dependency as an augmented conventional first-order network, and then feed it into GNNs to derive network embeddings. Moreover, we further propose a new end-to-end GNN framework for dealing with higher-order networks directly in the model. Specifically, the higher-order dependency is used as the neighbor aggregation controller when the node is embedded and updated. In the graph convolutional layer, in addition to the first-order neighbor information, we also aggregate the middle node information from the higher-order dependency segment. We finally test the new approaches on three real networks with higher-order dependency, and compare with some state-of-the-art methods. The results show significant improvements of the new approaches which consider higher-order dependency.

Graph Neural Networks (GNNs) have demonstrated great power in many network analytical tasks. However, graphs (i.e., networks) in the real world are usually text-rich, implying that valuable semantic information needs to be carefully considered. Existing GNNs for text-rich networks typically treat text as attribute words alone, which inevitably leads to the loss of important semantic structures, limiting the representation capability of GNNs. In this paper, we propose an end-to-end adaptive semantic architecture of graph convolutional networks, namely AS-GCN, which unifies neural topic model and graph convolutional networks, for text-rich network representation. Specifically, we utilize a neural topic model to extract the global topic semantics, and accordingly augment the original text-rich network into a tri-typed heterogeneous network, capturing both the local word-sequence semantic structure and the global topic semantic structure from text. We then design an effective semantic-aware propagation of information by introducing a discriminative convolution mechanism. We further propose two strategies, that is, distribution sharing and joint training, to adaptively generate a proper network structure based on the learning objective to improve network representation. Extensive experiments on text-rich networks illustrate that our new architecture outperforms the state-of-the-art methods by a significant improvement. Meanwhile, this architecture can also be applied to e-commerce search scenes, and experiments on a real e-commerce problem from JD further demonstrate the superiority of the proposed architecture over the baselines.

Graph convolutional networks (GCNs), aiming to obtain node embeddings by integrating high-order neighborhood information through stacked graph convolution layers, have demonstrated great power in many network analysis tasks such as node classification and link prediction. However, a fundamental weakness of GCNs, that is, topological limitations, including over-smoothing and local homophily of topology, limits their ability to represent networks. Existing studies for solving these topological limitations typically focus only on the convolution of features on network topology, which inevitably relies heavily on network structure. Moreover, most networks are text-rich, so it is important to integrate not only document-level information, but also the local text information which is particularly significant while often ignored by the existing methods. To solve these limitations, we propose BiTe-GCN, a novel GCN architecture modeling via bidirectional convolution of topology and features on text-rich networks. Specifically, we first transform the original text-rich network into an augmented bi-typed heterogeneous network, capturing both the global document-level information and the local text-sequence information from texts. We then introduce discriminative convolution mechanisms, which performs convolution on this augmented bi-typed network, realizing the convolutions of topology and features altogether in the same system, and learning different contributions of these two parts (i.e., network part and text part), automatically for the given learning objectives. Extensive experiments on text-rich networks demonstrate that our new architecture outperforms the state-of-the-arts by a breakout improvement. Moreover, this architecture can also be applied to several e-commerce search scenes such as JD searching, and experiments on JD dataset show the superiority of the proposed architecture over the related methods.