Hongyang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongyang Li has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Cui Zhu
Faculty of Information Technology, Beijing University of Technology, Beijing, 100020, China
2 shared publications - Wenjun Zhu
School of Computer Science, Faculty of Information Technology, Beijing University of Technology, Beijing, China
1 shared publication - Wenjun Zhu
Beijing University of Technology, Beijing, China
1 shared publication Xinyu Zhang
School of Computer Science, Faculty of Information Technology, Beijing University of Technology, Beijing, China
1 shared publication- Yunfeng Zhou
Faculty of Information Technology, Beijing University of Technology, Beijing, 100020, China
1 shared publication - Yunfeng Zhou
School of Computer Science, Faculty of Information Technology, Beijing University of Technology, Beijing, China
1 shared publication
Latest Publications
- 15 February 2024
- Published by Elsevier in Neural Networks
- Vol. 173, 106178
SCMEA: A stacked co-enhanced model for entity alignment based on multi-aspect information fusion and bidirectional contrastive learning
- 15 February 2024
- Published by Elsevier in Neural Networks
- Vol. 173, 106178
SCMEA: A stacked co-enhanced model for entity alignment based on multi-aspect information fusion and bidirectional contrastive learning
- Open Access
- 30 November 2023
- Published by IOS Press
- p. 728-739
Short-Term Sequential Pattern for Temporal Knowledge Graph Reasoning
Temporal knowledge graphs (TKGs) have been widely used in various fields, and predicting missing knowledge graph inference has been widely explored. However, the task of reasoning about potential future facts on TKGs is more challenging and has attracted the attention of researchers. As the unknowability of future events complicates inference, a thorough study of the characteristics of historical facts becomes crucial. The study of the concurrency of historical events and the underlying common patterns of relationships facilitates reasoning about future facts. In this paper, we propose a novel representation learning model based on Short-Term Sequential Patterns for TKG reasoning, namely STSP. By modeling TKG sequences recurrently and learning representations of entities and relations. Specifically, the STSP encoder uses three main modules. Concurrent facts for each timestamp are modeled using a convolution-based relation-aware GCN. The entityaware attention module is used to integrate the entity representation of the current timestamp and the previous timestamp. The sliding window mechanism is used to learn different relations sequentially. The entity and relation representations are then handed over to a translation-based decoder for final reasoning. We use four benchmark datasets to evaluate the proposed approach. The experimental results show that STSP out-performs state-of-the-art TKG reasoning methods and obtains substantial performance.
- 30 November 2023
- Published by IOS Press
- p. 728-739
Open AccessShort-Term Sequential Pattern for Temporal Knowledge Graph Reasoning
Temporal knowledge graphs (TKGs) have been widely used in various fields, and predicting missing knowledge graph inference has been widely explored. However, the task of reasoning about potential future facts on TKGs is more challenging and has attracted the attention of researchers. As the unknowability of future events complicates inference, a thorough study of the characteristics of historical facts becomes crucial. The study of the concurrency of historical events and the underlying common patterns of relationships facilitates reasoning about future facts. In this paper, we propose a novel representation learning model based on Short-Term Sequential Patterns for TKG reasoning, namely STSP. By modeling TKG sequences recurrently and learning representations of entities and relations. Specifically, the STSP encoder uses three main modules. Concurrent facts for each timestamp are modeled using a convolution-based relation-aware GCN. The entityaware attention module is used to integrate the entity representation of the current timestamp and the previous timestamp. The sliding window mechanism is used to learn different relations sequentially. The entity and relation representations are then handed over to a translation-based decoder for final reasoning. We use four benchmark datasets to evaluate the proposed approach. The experimental results show that STSP out-performs state-of-the-art TKG reasoning methods and obtains substantial performance.