Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.19042 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917424975052800 |
|---|---|
| author | Zhao, Shuyuan Chen, Wei Zhang, Weijie Hou, Xinrui Shen, Junfeng Shi, Boyan Guo, Shengnan Lin, Youfang Wan, Huaiyu |
| author_facet | Zhao, Shuyuan Chen, Wei Zhang, Weijie Hou, Xinrui Shen, Junfeng Shi, Boyan Guo, Shengnan Lin, Youfang Wan, Huaiyu |
| contents | Temporal Knowledge Graph (TKG) extrapolation aims to predict future events based on historical facts. Recent studies have attempted to enhance TKG extrapolation by integrating TKG's evolving structural representations and textual event chains into Large Language Models (LLMs). Yet, two main challenges limit these approaches: (1) The loss of essential spatial-temporal information due to shallow alignment between TKG's graph evolving structural representation and the LLM's semantic space, and (2) the progressive dilution of the TKG's evolving structural features during LLM fine-tuning. To address these challenges, we propose the Spatial-Temporal Knowledge Adapter (STK-Adapter), which flexibly integrates the evolving graph encoder and the LLM to facilitate TKG reasoning. In STK-Adapter, a Spatial-Temporal MoE is designed to capture spatial structures and temporal patterns inherent in TKGs. An Event-Aware MoE is employed to model intricate temporal semantics dependencies within event chains. In addition, a Cross-Modality Alignment MoE is proposed to facilitate deep cross-modality alignment by TKG-guided attention experts. Extensive experiments on benchmark datasets demonstrate that STK-Adapter significantly outperforms state-of-the-art methods and exhibits strong generalization capabilities in cross-dataset task. The code is available at https://github.com/Zhaoshuyuan0246/STK-Adapter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19042 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation Zhao, Shuyuan Chen, Wei Zhang, Weijie Hou, Xinrui Shen, Junfeng Shi, Boyan Guo, Shengnan Lin, Youfang Wan, Huaiyu Information Retrieval Temporal Knowledge Graph (TKG) extrapolation aims to predict future events based on historical facts. Recent studies have attempted to enhance TKG extrapolation by integrating TKG's evolving structural representations and textual event chains into Large Language Models (LLMs). Yet, two main challenges limit these approaches: (1) The loss of essential spatial-temporal information due to shallow alignment between TKG's graph evolving structural representation and the LLM's semantic space, and (2) the progressive dilution of the TKG's evolving structural features during LLM fine-tuning. To address these challenges, we propose the Spatial-Temporal Knowledge Adapter (STK-Adapter), which flexibly integrates the evolving graph encoder and the LLM to facilitate TKG reasoning. In STK-Adapter, a Spatial-Temporal MoE is designed to capture spatial structures and temporal patterns inherent in TKGs. An Event-Aware MoE is employed to model intricate temporal semantics dependencies within event chains. In addition, a Cross-Modality Alignment MoE is proposed to facilitate deep cross-modality alignment by TKG-guided attention experts. Extensive experiments on benchmark datasets demonstrate that STK-Adapter significantly outperforms state-of-the-art methods and exhibits strong generalization capabilities in cross-dataset task. The code is available at https://github.com/Zhaoshuyuan0246/STK-Adapter. |
| title | STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.19042 |