Zijie Xu
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
Research Subjects
Research Interests
Zijie Xu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Peng Wang
School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
4 shared publications - Jiajun Liu
School of Computer Science and Engineering, Southeast University, Nanjing, China
3 shared publications - Ziyu Shang
School of Computer Science and Engineering, Southeast University, Nanjing, Jiangsu, China
3 shared publications - Guozheng Li
School of Computer Science and Engineering, Southeast University, Nanjing, Jiangsu, China
2 shared publications - Guozheng Li
School of Computer Science and Engineering, Southeast University
1 shared publication Jiajun Liu
School of Computer Science and Engineering Southeast University China
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3964-3973
Unlearning of Knowledge Graph Embedding via Preference Optimization
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3964-3973
Open AccessUnlearning of Knowledge Graph Embedding via Preference Optimization
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (9) , 5360-5377
Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning
Knowledge graph reasoning (KGR) seeks to infer new factual triples from existing knowledge graphs (KGs). Recent methods have unified transductive and inductive reasoning by learning entity-independent representations through local neighboring structures. Nevertheless, these methods often encounter inefficiencies and rely on elaborate local structures without directly modeling the correlations between queries and various structures within KGs. In this paper, we propose a novel framework MulGA, which is designed to learn multi-granularity and adaptive embeddings for KGR. MulGA first employs connectivity subgraphs to uniformly and hierarchically represent query-related structures within KGs, such as triples, relation paths, and subgraphs, establishing the hierarchical relationship between structures at different granularities. Subsequently, we design a graph neural network-based multi-granularity embedding propagation module that unifies the message-passing process with the connectivity subgraph construction. This module obtains the query-related structural representations by all entities at multiple granularities, eliminating the need to explicitly extract any graph elements, thus addressing inefficiency issues. Moreover, we develop a structure-aware adaptive merging mechanism that assigns weights to different granularities and integrates them into cohesive subgraph-granularity representations for reasoning. The systematic experiments have been conducted on 15 benchmarks and MulGA achieves a significant improvement in MRR by an average of 0.5% -1.1% on transductive tasks and 0.2% -7.3% on inductive tasks than existing state-of-the-art methods. Moreover, MulGA exhibits faster convergence speed, smaller number of parameters, competitive inference time, and alleviates the over-smoothing prevalent in graph neural networks.
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (9) , 5360-5377
Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning
Knowledge graph reasoning (KGR) seeks to infer new factual triples from existing knowledge graphs (KGs). Recent methods have unified transductive and inductive reasoning by learning entity-independent representations through local neighboring structures. Nevertheless, these methods often encounter inefficiencies and rely on elaborate local structures without directly modeling the correlations between queries and various structures within KGs. In this paper, we propose a novel framework MulGA, which is designed to learn multi-granularity and adaptive embeddings for KGR. MulGA first employs connectivity subgraphs to uniformly and hierarchically represent query-related structures within KGs, such as triples, relation paths, and subgraphs, establishing the hierarchical relationship between structures at different granularities. Subsequently, we design a graph neural network-based multi-granularity embedding propagation module that unifies the message-passing process with the connectivity subgraph construction. This module obtains the query-related structural representations by all entities at multiple granularities, eliminating the need to explicitly extract any graph elements, thus addressing inefficiency issues. Moreover, we develop a structure-aware adaptive merging mechanism that assigns weights to different granularities and integrates them into cohesive subgraph-granularity representations for reasoning. The systematic experiments have been conducted on 15 benchmarks and MulGA achieves a significant improvement in MRR by an average of 0.5% -1.1% on transductive tasks and 0.2% -7.3% on inductive tasks than existing state-of-the-art methods. Moreover, MulGA exhibits faster convergence speed, smaller number of parameters, competitive inference time, and alleviates the over-smoothing prevalent in graph neural networks.
- Open Access
Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction
The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.
Open AccessUnlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction
The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.
- 15 April 2023
- Published by Springer Nature
- p. 534-543
A Two-Stage Label Rectification Framework for Noisy Event Extraction
- 15 April 2023
- Published by Springer Nature
- p. 534-543
A Two-Stage Label Rectification Framework for Noisy Event Extraction