Graph clustering, which aims to divide nodes in the graph into several distinct clusters, is a fundamental yet challenging task. Benefiting from the powerful representation capability of deep learning, deep graph clustering methods have achieved great success in recent years. However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field. From this motivation, we conduct a comprehensive survey of deep graph clustering. Firstly, we introduce formulaic definition, evaluation, and development in this field. Secondly, the taxonomy of deep graph clustering methods is presented based on four different criteria, including graph type, network architecture, learning paradigm, and clustering method. Thirdly, we carefully analyze the existing methods via extensive experiments and summarize the challenges and opportunities from five perspectives, including graph data quality, stability, scalability, discriminative capability, and unknown cluster number. Besides, the applications of deep graph clustering methods in six domains, including computer vision, natural language processing, recommendation systems, social network analyses, bioinformatics, and medical science, are presented. Last but not least, this paper provides open resource supports, including 1) a collection (https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering) of state-of-the-art deep graph clustering methods (papers, codes, and datasets) and 2) a flexible and extensible Python library (https://github.com/Marigoldwu/PyDGC) for deep graph clustering. We hope this work can serve as a quick guide and help researchers overcome challenges in this vibrant field.

Multi-hop Knowledge Base Question Answering (KBQA) aims to find answer entities in the knowledge base that are multiple hops away from the entities in the question. Information retrieval-based (IR-based) methods extract a pivotal subgraph from the entire KB to locate candidate answers and then evaluate their plausibility through semantic matching with the question. However, we observed that the extracted subgraphs often include nodes that are weakly related or irrelevant to the question. Without a proper node filtering mechanism, the number of irrelevant nodes grows as the number of hops increases, leading to excessive consumption of computational resources. To address these challenges, this study introduces an efficient LLM-based subgraph retrieval method for multi-hop knowledge base question answering, M-ER. The framework leverages Monte Carlo Tree Search (MCTS) to transform subgraph exploration into a tree-structured search process. During the MCTS selection phase, nodes that are highly relevant to the question are prioritized for inclusion in the subgraph, eliminating the need to traverse all nodes in the KB. The framework further incorporates a large language model (LLM) to refine the search direction, ensuring that exploration remains focused on nodes relevant to the question. In addition, selected nodes are quantitatively scored, and these scores are fed back into the node selection process to effectively filter out irrelevant candidates, thereby improving the quality of the subgraph. This mechanism not only narrows the search space but also enhances the overall efficiency of multi-hop KBQA. Experiments on the WebQSP benchmark demonstrate that M-ER achieves 78.88% on the Hits@1 metric, while also improving computational efficiency. These results not only validate the effectiveness of M-ER, but also offer a viable technical path to balance performance and computational efficiency.

Inductive relation prediction aims to predict missing connections between entities unseen during training. Recent approaches adopt binary (positive or negative) training labels, which indicate whether the query relation exists between the entities, as supervision to teach models recognizing the entity-independent relation patterns in the context (enclosed subgraph or connective path). However, we argue that in this kind of method, the trained models are guided to make relation predictions by remembering whether the query relation and its contextual relational pattern co-occur more frequently in positive or negative samples. This solution could introduce two major limitations: 1) the model struggles with long-tail combinations, i.e., the combination between query relation and the relational pattern rarely occurs during training; 2) when noisy relational patterns, which fail to provide evidence for predicting the query relation, frequently occur with the query relation in positive training samples, the model will be misled into considering the noisy relational patterns as a feature supporting the existence of the query relation. To solve these problems, we propose ToC (Thinking on Context). ToC first utilizes large language models (LLMs) to incorporate a chain of thought as an additional supervisory constraint, guiding the model to make relational predictions based on logical reasoning instead of co-occurrence frequency. Additionally, ToC employs the reasoning capabilities of LLMs to construct context-level negative samples, aiding the model in identifying and disregarding noisy relational patterns. Extensive experiments show that ToC significantly outperforms state-of-the-art methods across three widely used datasets in multiple inductive settingshttps://github.com/AI-Chen/ToC_KGC.

The ubiquity of Graph Neural Networks (GNNs) emphasizes the imperative to assess their resilience against node injection attacks, a type of evasion attacks that impact victim models by injecting nodes with fabricated attributes and structures. However, prevailing attacks face two primary limitations: (1) Sequential construction of attributes and structures results in suboptimal outcomes as structure information is overlooked during attribute construction and vice versa. (2) In black-box scenarios, where attackers lack access to victim model architecture and parameters, reliance on surrogate models degrades performance due to architectural discrepancies. To overcome these limitations, we introduce GZOO, a black-box node injection attack that leverages an adversarial graph generator, compromising both attribute and structure sub-generators. This integration crafts optimal attributes and structures by considering their mutual information, enhancing their influence when aggregating information from injected nodes. Furthermore, GZOO proposes a zeroth-order optimization algorithm leveraging prediction results from victim models to estimate gradients for updating generator parameters, eliminating the necessity to train surrogate models. Across sixteen datasets, GZOO significantly outperforms state-of-the-art attacks, achieving remarkable effectiveness and robustness. Notably, on the Cora dataset with the GCN model, GZOO achieves an impressive 95.69% success rate, surpassing the maximum 66.01% achieved by baselines.

Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance of the GNNs in this field. To alleviate the collapse of node representations in semi-supervised scenario, we propose a novel graph contrastive learning method, termed M ixed G raph C ontrastive N etwork (MGCN). In our method, we improve the discriminative capability of the latent embeddings by an interpolation-based augmentation strategy and a correlation reduction mechanism. Specifically, we first conduct the interpolation-based augmentation in the latent space and then force the prediction model to change linearly between samples. Second, we enable the learned network to tell apart samples across two interpolation-perturbed views through forcing the correlation matrix across views to approximate an identity matrix. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discriminative representation learning. Extensive experimental results on six datasets demonstrate the effectiveness and the generality of MGCN compared to the existing state-of-the-art methods. The code of MGCN is available at https://github.com/xihongyang1999/MGCN on Github.

Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely leveraged in graph learning as an effective mechanism to enhance the discriminative capacity of the learned representations. However, the complex structures of KG make it hard to construct appropriate contrastive pairs. Only a few attempts have integrated contrastive learning strategies with KGE. But, most of them rely on language models (e.g.,Bert) for contrastive pair construction instead of fully mining information underlying the graph structure, hindering expressive ability. Surprisingly, we find that the entities within a relational symmetrical structure are usually similar and correlated. To this end, we propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL, which mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models. Concretely, a plug-and-play approach is proposed by taking entities in the relation-symmetrical positions as positive pairs. Besides, a self-supervised alignment loss is designed to pull together positive pairs. Experimental results on link prediction and entity classification datasets demonstrate that our KGE-SymCL can be easily adopted to various KGE models for performance improvements. Moreover, extensive experiments show that our model could outperform other state-of-the-art baselines.

Federated knowledge graph reasoning (FedKGR) aims to perform reasoning over different clients while protecting data privacy, drawing increasing attention to its high practical value. Previous works primarily focus on data heterogeneity, ignoring challenges from limited data scale and primitive negative sample strategies, i.e., random entity replacement, which yield low-quality negatives and zero loss issues. Meanwhile, generative adversarial networks (GANs) are widely used in different fields to generate high-quality negative samples, but no work has been developed for FedKGR. To this end, we propose a plug-and-playEntity-awareAdversarialNegative sampling strategy for FedKGR, termed FedEAN. Specifically, we are the first to adopt GANs to generate high-quality negative samples in different clients. It takes the target triplet in each batch as input and outputs high-quality negative samples, which guaranteed by the joint training of the generator and discriminator. Moreover, we design an entity-aware adaptive negative sampling mechanism based on the similarity of entity representations before and after server aggregation, which can persevere the entity global consistency across clients during training. Extensive experiments demonstrate that FedEAN excels with various FedKGR backbones, demonstrating its ability to construct high-quality negative samples and address the zero-loss issue.

Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferior representations for downstream evaluations. To address this issue, we propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space. Through both theoretical and empirical analyses, we have discovered that performing a joint mask-then-reconstruct strategy in both latent feature and raw data spaces could yield improved stability and performance. To this end, we elaborately design a masked latent feature completion scheme, which predicts latent features of masked nodes under the guidance of high-order sample correlations that are hard to be observed from the raw data perspective. Specifically, we first adopt a latent feature predictor to predict the masked latent features from the visible ones. Next, we encode the raw data of masked samples with a momentum graph encoder and subsequently employ the resulting representations to improve the predicted results through latent feature matching. Extensive experiments on seventeen datasets have demonstrated the effectiveness and robustness of RARE against state-of-the-art (SOTA) competitors across three downstream tasks. Our source code is available athttps://github.com/WxTu/RARE.

Multi-view clustering has attracted increasing attention in data mining communities. Despite superior clustering performance, we observe that existing multi-view subspace clustering methods directly fuse multi-view information in the similarity level by merging noisy affinity matrices; and isolate the processes of affinity learning, multiple information fusion and clustering. Both factors may cause insufficient utilization of multi-view information, leading to unsatisfying clustering performance. This paper proposes a novel consensus one-step multi-view subspace clustering (COMVSC) method to address these issues. Instead of directly fusing affinity matrices, COMVSC optimally integrates discriminative partition-level information, which is helpful in eliminating noise among data. Moreover, the affinity matrices, consensus representation and final clustering labels are learned simultaneously in a unified framework. Extensive experiment results on benchmark datasets demonstrate the superiority of our method over other state-of-the-art approaches.

Reasoning on temporal knowledge graphs (TKGR), aiming to infer missing events along the timeline, has been widely studied to alleviate incompleteness issues in TKG, which is composed of a series of KG snapshots at different timestamps. Two types of information, i.e., intra-snapshot structural information and inter-snapshot temporal interactions, mainly contribute to the learned representations for reasoning in previous models. However, these models fail to leverage (1) semantic correlations between relationships for the former information and (2) the periodic temporal patterns along the timeline for the latter one. Thus, such insufficient mining manners hinder expressive ability, leading to sub-optimal performances. To address these limitations, we propose a novel reasoning model, termed RPC, which sufficiently mines the information underlying the Relational correlations and Periodic patterns via two novel Correspondence units, i.e., relational correspondence unit (RCU) and periodic correspondence unit (PCU). Concretely, relational graph convolutional network (RGCN) and RCU are used to encode the intra-snapshot graph structural information for entities and relations, respectively. Besides, the gated recurrent units (GRU) and PCU are designed for sequential and periodic inter-snapshot temporal interactions, separately. Moreover, the model-agnostic time vectors are generated by time2vector encoders to guide the time-dependent decoder for fact scoring. Extensive experiments on six benchmark datasets show that RPC outperforms the state-of-the-art TKGR models, and also demonstrate the effectiveness of two novel strategies in our model.

Multi-view spectral clustering can effectively reveal the intrinsic cluster structure among data by performing clustering on the learned optimal embedding across views. Though demonstrating promising performance in various applications, most of existing methods usually linearly combine a group of pre-specified first-order Laplacian matrices to construct the optimal Laplacian matrix, which may result in limited representation capability and insufficient information exploitation. Also, storing and implementing complex operations on the{$n\times n}$Laplacian matrices incurs intensive storage and computation complexity. To address these issues, this paper first proposes a multi-view spectral clustering algorithm that learns a high-order optimal neighborhood Laplacian matrix, and then extends it to the late fusion version for accurate and efficient multi-view clustering. Specifically, our proposed algorithm generates the optimal Laplacian matrix by searching the neighborhood of the linear combination of both the first-order and high-order base Laplacian matrices simultaneously. By this way, the representative capacity of the learned optimal Laplacian matrix is enhanced, which is helpful to better utilize the hidden high-order connection information among data, leading to improved clustering performance. We design an efficient algorithm with proved convergence to solve the resultant optimization problem. Extensive experimental results on nine datasets demonstrate the superiority of the proposed algorithm

Multiple kernel clustering (MKC) algorithm aims to group data into different categories by optimally integrating information from a group of pre-specified kernels. Though demonstrating superiorities in various applications, we observe that existing MKC algorithms usuallydo not sufficiently consider the local density around individual data samplesandexcessively limit the representation capacity of the learned optimal kernel, leading to unsatisfying performance. In this paper, we propose an algorithm, called optimal neighborhood MKC with adaptive local kernels (ON-ALK), to address the two issues. In specific, we construct adaptive local kernels to sufficiently consider the local density around individual data samples, where different numbers of neighbors are discriminatingly selected on each sample. Further, the proposed ON-ALK algorithm boosts the representation of the learned optimal kernel via relaxing it into the neighborhood area of weighted combination of the pre-specified kernels. To solve the resultant optimization problem, a three-step iterative algorithm is designed and theoretically proven to be convergent. After that, we also study the generalization bound of the proposed algorithm. Extensive experiments have been conducted to evaluate the clustering performance. As indicated, the algorithm significantly outperforms state-of-the-art methods in recent literatures on six challenging benchmark datasets, verifying its advantages and effectiveness.

Multi-view clustering has attracted increasing attention in multimedia, machine learning and data mining communities. As one kind of the essential multi-view clustering algorithm, multi-view subspace clustering (MVSC) becomes more and more popular due to its strong ability to reveal the intrinsic low dimensional clustering structure hidden across views. Despite superior clustering performance in various applications, we observe that existing MVSC methodsdirectly fuse multi-view information in the similarity level by merging noisy affinity matrices; andisolate the processes of affinity learning, multi-view information fusion and clustering. Both factors may cause insufficient utilization of multi-view information, leading to unsatisfying clustering performance. This paper proposes a novel consensus one-step multi-view subspace clustering (COMVSC) method to address these issues. Instead of directly fusing multiple affinity matrices, COMVSC optimally integrates discriminative partition-level information, which is helpful to eliminate noise among data. Moreover, the affinity matrices, consensus representation and final clustering labels matrix are learned simultaneously in a unified framework. By doing so, the three steps can negotiate with each other to best serve the clustering task, leading to improved performance. Accordingly, we propose an iterative algorithm to solve the resulting optimization problem. Extensive experiment results on benchmark datasets demonstrate the superiority of our method against other state-of-the-art approaches.