Search papers, labs, and topics across Lattice.
The paper introduces STK-Adapter, a novel approach for temporal knowledge graph (TKG) extrapolation that integrates evolving graph structures and event chains into LLMs. It addresses the limitations of shallow alignment and feature dilution by using a Spatial-Temporal Mixture of Experts (MoE) to capture spatial-temporal patterns and an Event-Aware MoE to model temporal semantics. Experiments on benchmark datasets demonstrate that STK-Adapter significantly outperforms state-of-the-art methods and generalizes well across datasets.
Forget shallow alignment – STK-Adapter deeply fuses evolving knowledge graph structure and event chains into LLMs, unlocking superior temporal reasoning.
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.
