Personalized exercise recommendation systems aim to enhance learning efficiency by dynamically guiding students toward content aligned with their evolving knowledge states. Among various approaches, Reinforcement Learning (RL) has emerged as an effective framework for modeling student-environment interactions as sequential decision-making processes. However, most existing RL-based methods typically reward recommendations that target unmastered knowledge concepts.Such reward-driven strategies are prone to local optima, restricting exploration of unattempted or less familiar knowledge concepts. In addition, they often overlook key learning factors, such as forgetting dynamics and exercise difficulty, leading to suboptimal outcomes. To address these issues, we propose a novelIntegratingEntropyRegulation andDual-objectiveOptimizationExerciseRecommendation (IERDO-ER)method. Specifically, we introduce an entropy-based function to encourage broader exploration in the exercise space. We also design an end-to-end policy network that generates candidate exercises as next-step actions for the recommendation agent. To enable more adaptive and pedagogically sound recommendations, we develop a dual-objective reward mechanism that incorporates both anti-forgetting and gentleness objectives. This mechanism continuously balances policy optimization through a synergy of rewards and penalties. Experiments on three real-world educational datasets show that our approach consistently outperforms strong baselines, validating its effectiveness.

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.

Multi-Domain Recommendation (MDR) achieves the desirable recommendation performance by effectively utilizing the transfer information across different domains. Despite the great success, most existing MDR methods adopt a single structure to transfer complex domain-shared knowledge. However, the beneficial transferring information should vary across different domains. When there is knowledge conflict between domains or a domain is of poor quality, unselectively leveraging information from all domains will lead to a serious Negative Transfer Problem (NTP). Therefore, how to effectively model the complex transfer relationships between domains to avoid NTP is still a direction worth exploring. To address these issues, we propose a simple and dynamic Similar Domain Selection Principle (SDSP) for multi-domain recommendation in this paper. SDSP presents the initial exploration of selecting suitable domain knowledge for each domain to alleviate NTP. Specifically, we propose a novel prototype-based domain distance measure to effectively model the complexity relationship between domains. Thereafter, the proposed SDSP can dynamically find similar domains for each domain based on the supervised signals of the domain metrics and the unsupervised distance measure from the learned domain prototype. We emphasize that SDSP is a lightweight method that can be incorporated with existing MDR methods for better performance while not introducing excessive time overheads. To the best of our knowledge, it is the first solution that can explicitly measure domain-level gaps and dynamically select appropriate domains in the MDR field. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method.

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.

Graph anomaly detection (GAD) on attributed networks aims to capture abnormal nodes whose attributes or structures differ significantly from most nodes. The existing GAD models amplify the representation differences between normal and abnormal nodes to identify anomalies via carefully designed feature extraction modules. However, these models ignore the bottlenecks encountered by abnormal nodes in message passing. In particular, when the anomalies occurs at critical crossroads, the information of multiple nodes is compressed into a fixed-length representation, and the resulting over-squashing weakens the abnormal information. To address this, we propose an unsupervisedSTructural optimization model guided by sIMilarity reconstruction (STIM). Specifically, we define redundant edges that cause over-squashing, design the Neighbor-Structure Optimization module to filter redundant edges through the edge-dropping strategy based on critical crossroads, and optimize the graph structure to alleviate over-squashing. In addition, to alleviate the over-smoothing caused by the high inter-class node similarity of the data itself and the edge-dropping strategy, we design the Neighbor-Similarity Reconstruction module based on similarity calculation, which guides the model to expand inter-class variation. Extensive experiments on benchmark datasets show that STIM can effectively optimize message passing and improve anomaly detection performance. The source code is available athttps://github.com/Junyi-Yan/STIM.

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.

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.

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.