Author name cluster

Enjun Du

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

TIST Journal 2026 Journal Article

Causal Disentanglement-Enhanced Diffusion Denoising for Social Recommendation

Shixiao Yang
Zhida Qin
Enjun Du
Haoyan Fu
Haoyao Zhang
Pengzhan Zhou
Tianyu Huang
Gangyi Ding

In recent years, social recommendation systems have emerged as a pivotal technology for enhancing recommendation accuracy by leveraging user social homophily and influence. Although many works have been devoted to this area, existing works still struggle to extract the beneficial structural information from social relationships that is beneficial for recommendations and neglect the inherent popularity bias in the social networks, which leads to suboptimal recommendation performances. To address these challenges, we propose a novel framework termed Causal Disentanglement-Enhanced Diffusion Denoising for Social Recommendation (CaDDiSR). This framework first employs causal graphs to disentangle the complexities of social relationships, generating user representations with high-order structures, which are subsequently used as inputs to a diffusion process to effectively denoise social networks and retain social signals beneficial for recommendation tasks. Furthermore, the framework integrates a bidirectional knowledge distillation mechanism, which balances user representations between social and recommendation contexts, thereby facilitating the effective fusion of their respective advantages while simultaneously mitigating noise interference and enhancing overall system performance. Finally, cross-domain contrastive learning is utilized to optimize user and item representations, ensuring consistency in recommendation performance across diverse scenarios. Experimental results on multiple real-world datasets demonstrate that CaDDiSR significantly outperforms existing baseline models, substantiating its superior performance.

Details DOI

AAAI Conference 2026 Conference Paper

GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs

Enjun Du
Siyi Liu
Yongqi Zhang

Knowledge graph reasoning in the fully-inductive setting—where both entities and relations at test time are unseen during training—remains an open challenge. In this work, we introduce GraphOracle, a novel framework that achieves robust fully-inductive reasoning by transforming each knowledge graph into a Relation-Dependency Graph (RDG). The RDG encodes directed precedence links between relations, capturing essential compositional patterns while drastically reducing graph density. Conditioned on a query relation, a multi-head attention mechanism propagates information over the RDG to produce context-aware relation embeddings. These embeddings then guide a second GNN to perform inductive message passing over the original knowledge graph, enabling prediction on entirely new entities and relations. Comprehensive experiments on 60 benchmarks demonstrate that GraphOracle outperforms prior methods by up to 25% in fully-inductive and 28% in cross-domain scenarios. Our analysis further confirms that the compact RDG structure and attention-based propagation are key to efficient and accurate generalization

PDF Details DOI

AIJ Journal 2026 Journal Article

Neural knowledge graph reasoning with relational digraph

Yongqi Zhang
Haiquan Qiu
Shuzhi Liu
Enjun Du
Quanming Yao

Reasoning on Knowledge Graphs (KGs) aims to deduce unobserved facts from established ones. While path-based methods are interpretable and transferable, they struggle to capture complex graph topologies. Conversely, subgraph-based approaches preserve structure but often face high computational overhead. To unify these strengths, we introduce the relational directed graph (r-digraph), a structure that generalizes relational paths into layered subgraphs to capture rich local evidence. To overcome the computational burden of processing individual subgraphs, we propose RED-GNN. By observing that r-digraphs for a common query share overlapping paths, RED-GNN utilizes dynamic programming to recursively encode multiple r-digraphs with shared edges. Furthermore, to address the dynamic nature of real-world facts, we extend this framework to T-RED-GNN for temporal knowledge graphs (tKGs). T-RED-GNN introduces a relative temporal encoding mechanism that enables a unified approach to both interpolation and extrapolation tasks. Extensive experiments show that our methodologies significantly outperform state-of-the-art static and temporal reasoning models. Moreover, the learned attention weights provide transparent, interpretable evidence for the reasoning process.

Details DOI

NeurIPS Conference 2025 Conference Paper

GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments

Enjun Du
Xunkai Li
Tian Jin
Zhihan Zhang
Rong-Hua Li
Guoren Wang

The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph data synthesis techniques primarily focus on simplistic structural operations, lacking the capacity to generate semantically rich nodes with meaningful textual attributes—a critical limitation for real-world applications. While large language models (LLMs) demonstrate exceptional text generation capabilities, their direct application to graph synthesis is impeded by context window limitations, hallucination phenomena, and structural consistency challenges. To address these issues, we introduce \textbf{GraphMaster}—the first multi-agent framework specifically designed for graph data synthesis in data-limited environments. GraphMaster orchestrates four specialized LLM agents (Manager, Perception, Enhancement, and Evaluation) that collaboratively optimize the synthesis process through iterative refinement, ensuring both semantic coherence and structural integrity. To rigorously evaluate our approach, we create new data-limited “Sub” variants of six standard graph benchmarks, specifically designed to test synthesis capabilities under realistic constraints. Additionally, we develop a novel interpretability assessment framework that combines human evaluation with a principled Grassmannian manifold-based analysis, providing both qualitative and quantitative measures of semantic coherence. Experimental results demonstrate that GraphMaster significantly outperforms traditional synthesis methods across multiple datasets, establishing a strong foundation for advancing GFMs in data-scarce environments.

PDF Details