TL;DR
STK-Adapter introduces a novel framework that effectively integrates evolving graph structures and event chains into LLMs for improved temporal knowledge graph extrapolation, addressing key challenges in information preservation and alignment.
Contribution
It proposes the Spatial-Temporal Knowledge Adapter with specialized MoEs to enhance TKG reasoning and cross-modality alignment within LLMs.
Findings
Outperforms state-of-the-art methods on benchmark datasets.
Demonstrates strong generalization in cross-dataset tasks.
Effectively captures spatial, temporal, and semantic dependencies.
Abstract
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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
