Zequn Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zequn Sun has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Wei Hu
Nanjing University
16 shared publications - Yuanning Cui
Nanjing University of Information Science and Technology
4 shared publications - Yang Liu
Nanjing University
3 shared publications - Jiacheng Huang
Nanjing University, Nanjing, China
2 shared publications - Lingbing Guo
College of Intelligence and Computing, Tianjin University, Tianjin, China
2 shared publications - Qijin Chen
Alibaba Group, Hangzhou, China
2 shared publications
Latest Publications
- 6 November 2026
- Published by Springer Nature
- p. 143-158
Knowledge Graph Completion with Iterative Self-reflection of Retrieval-Augmented Language Models
- 6 November 2026
- Published by Springer Nature
- p. 143-158
Knowledge Graph Completion with Iterative Self-reflection of Retrieval-Augmented Language Models
- 23 October 2026
- Published by Springer Nature
- p. 260-281
Mitigating Exploration Sluggishness in Iterative Knowledge Graph Augmentation
- 23 October 2026
- Published by Springer Nature
- p. 260-281
Mitigating Exploration Sluggishness in Iterative Knowledge Graph Augmentation
- Open Access
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. However, existing methods that rely on finetuned LLMs or GNN retrievers are limited by dataset-specific tuning and scalability on large or unseen graphs. We propose the LLM-KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR). KGFR encodes relations using LLM-generated descriptions and initializes entities based on their roles in the question, enabling zero-shot generalization to unseen KGs. To handle large graphs efficiently, it employs Asymmetric Progressive Propagation (APP)- a stepwise expansion that selectively limits high-degree nodes while retaining informative paths. Through node-, edge-, and path-level interfaces, the LLM iteratively requests candidate answers, supporting facts, and reasoning paths, forming a controllable reasoning loop. Experiments demonstrate that LLM-KGFR achieves strong performance while maintaining scalability and generalization, providing a practical solution for KG-augmented reasoning.
Open AccessKGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. However, existing methods that rely on finetuned LLMs or GNN retrievers are limited by dataset-specific tuning and scalability on large or unseen graphs. We propose the LLM-KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR). KGFR encodes relations using LLM-generated descriptions and initializes entities based on their roles in the question, enabling zero-shot generalization to unseen KGs. To handle large graphs efficiently, it employs Asymmetric Progressive Propagation (APP)- a stepwise expansion that selectively limits high-degree nodes while retaining informative paths. Through node-, edge-, and path-level interfaces, the LLM iteratively requests candidate answers, supporting facts, and reasoning paths, forming a controllable reasoning loop. Experiments demonstrate that LLM-KGFR achieves strong performance while maintaining scalability and generalization, providing a practical solution for KG-augmented reasoning.
- 29 October 2025
- Published by Springer Nature
- p. 77-95
Are LLMs Really Knowledgeable for Knowledge Graph Completion?
- 29 October 2025
- Published by Springer Nature
- p. 77-95
Are LLMs Really Knowledgeable for Knowledge Graph Completion?
- 17 March 2025
- Published by IOS Press
Knowledge Fusion
Knowledge fusion aims to integrate different knowledge graphs into a unified, consistent, and concise format, thereby establishing interoperability for applications that leverage multi-source knowledge. In this chapter, we introduce the research process of knowledge fusion. We begin with an exploration of the fundamental principles of multi-source knowledge fusion, followed by a survey of the technical advancements in knowledge fusion. Subsequently, we outline potential future research directions and conclude with a summary. We believe that the combination and mutual promotion of knowledge fusion and other knowledge graph technologies will make a big difference.
- 17 March 2025
- Published by IOS Press
Knowledge Fusion
Knowledge fusion aims to integrate different knowledge graphs into a unified, consistent, and concise format, thereby establishing interoperability for applications that leverage multi-source knowledge. In this chapter, we introduce the research process of knowledge fusion. We begin with an exploration of the fundamental principles of multi-source knowledge fusion, followed by a survey of the technical advancements in knowledge fusion. Subsequently, we outline potential future research directions and conclude with a summary. We believe that the combination and mutual promotion of knowledge fusion and other knowledge graph technologies will make a big difference.
- 20 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (5) , 3062-3074
Transfer-and-Fusion: Integrated Link Prediction Across Knowledge Graphs
Existing work on knowledge graph (KG) link prediction has primarily focused on a single KG. However, a single KG is often limited by its incompleteness, encompassing missing facts, entities, and relations. This limitation subsequently restricts the practicality, as it cannot handle the queries that involve missing entities or relations within the single KG. In this paper, we explore an extended link prediction task, cross-KG link prediction, which answers queries using entities or relations integrated from other KGs. The crux of this problem is transferring knowledge across KGs and fusing their embedding spaces, which possess varying schemata. We develop a relation prototype graph to model the interactions among relations from different KGs. Based on this graph, we first propose a dual-view embedding learning module to fuse embedding spaces by training with instance facts and relation prototype edges. We then introduce an attention mechanism to highlight pivotal information for specific queries, recognizing that different KGs often emphasize various domains. Moreover, we devise an augmentation strategy to generate pseudo-cross-KG facts, facilitating knowledge transfer across KGs. Using four widely-used KGs, we construct two cross-KG link prediction datasets. Extensive experimental results demonstrate the superiority of our model and the unique contributions of each module.
- 20 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (5) , 3062-3074
Transfer-and-Fusion: Integrated Link Prediction Across Knowledge Graphs
Existing work on knowledge graph (KG) link prediction has primarily focused on a single KG. However, a single KG is often limited by its incompleteness, encompassing missing facts, entities, and relations. This limitation subsequently restricts the practicality, as it cannot handle the queries that involve missing entities or relations within the single KG. In this paper, we explore an extended link prediction task, cross-KG link prediction, which answers queries using entities or relations integrated from other KGs. The crux of this problem is transferring knowledge across KGs and fusing their embedding spaces, which possess varying schemata. We develop a relation prototype graph to model the interactions among relations from different KGs. Based on this graph, we first propose a dual-view embedding learning module to fuse embedding spaces by training with instance facts and relation prototype edges. We then introduce an attention mechanism to highlight pivotal information for specific queries, recognizing that different KGs often emphasize various domains. Moreover, we devise an augmentation strategy to generate pseudo-cross-KG facts, facilitating knowledge transfer across KGs. Using four widely-used KGs, we construct two cross-KG link prediction datasets. Extensive experimental results demonstrate the superiority of our model and the unique contributions of each module.
- 27 November 2024
- Published by Springer Nature
- p. 199-217
Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
- 27 November 2024
- Published by Springer Nature
- p. 199-217
Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
- Open Access
Distributed Representations of Entities in Open-World Knowledge Graphs
Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings.
Open AccessDistributed Representations of Entities in Open-World Knowledge Graphs
Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings.
- Open Access
Generating Explanations to Understand and Repair Embedding-based Entity Alignment
Entity alignment (EA) seeks identical entities in different knowledge graphs, which is a long-standing task in the database research. Recent work leverages deep learning to embed entities in vector space and align them via nearest neighbor search. Although embedding-based EA has gained marked success in recent years, it lacks explanations for alignment decisions. In this paper, we present the first framework that can generate explanations for understanding and repairing embedding-based EA results. Given an EA pair produced by an embedding model, we first compare its neighbor entities and relations to build a matching subgraph as a local explanation. We then construct an alignment dependency graph to understand the pair from an abstract perspective. Finally, we repair the pair by resolving three types of alignment conflicts based on dependency graphs. Experiments on a variety of EA datasets demonstrate the effectiveness, generalization, and robustness of our framework in explaining and repairing embedding-based EA results.
Open AccessGenerating Explanations to Understand and Repair Embedding-based Entity Alignment
Entity alignment (EA) seeks identical entities in different knowledge graphs, which is a long-standing task in the database research. Recent work leverages deep learning to embed entities in vector space and align them via nearest neighbor search. Although embedding-based EA has gained marked success in recent years, it lacks explanations for alignment decisions. In this paper, we present the first framework that can generate explanations for understanding and repairing embedding-based EA results. Given an EA pair produced by an embedding model, we first compare its neighbor entities and relations to build a matching subgraph as a local explanation. We then construct an alignment dependency graph to understand the pair from an abstract perspective. Finally, we repair the pair by resolving three types of alignment conflicts based on dependency graphs. Experiments on a variety of EA datasets demonstrate the effectiveness, generalization, and robustness of our framework in explaining and repairing embedding-based EA results.
- 29 February 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 290
Distributed representations of entities in open-world knowledge graphs
- 29 February 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 290
Distributed representations of entities in open-world knowledge graphs