Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

TL;DR

This paper introduces TransFIR, a framework for inductive reasoning on temporal knowledge graphs that effectively leverages semantic similarities to improve reasoning about emerging entities.

Contribution

It proposes a novel codebook-based classifier that clusters entities semantically, enabling transfer of reasoning patterns to emerging entities in TKGs.

Findings

TransFIR outperforms baselines with an average 28.6% MRR improvement.

Emerging entities constitute about 25% of TKGs and lack historical interactions.

Semantic similarity among entities enables transfer of interaction patterns.

Abstract

Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts. While existing methods are effective at capturing relational dynamics, their performance is limited by a closed-world assumption, which fails to account for emerging entities not present in the training. Notably, these entities continuously join the network without historical interactions. Empirical study reveals that emerging entities are widespread in TKGs, comprising roughly 25\% of all entities. The absence of historical interactions of these entities leads to significant performance degradation in reasoning tasks. Whereas, we observe that entities with semantic similarities often exhibit comparable interaction histories, suggesting the presence of transferable temporal patterns. Inspired by this insight, we propose TransFIR (Transferable Inductive Reasoning), a novel framework that leverages historical interaction sequences from semantically similar known entities to support inductive reasoning. Specifically, we propose a codebook-based classifier that categorizes emerging entities into latent semantic clusters, allowing them to adopt reasoning patterns from similar entities. Experimental results demonstrate that TransFIR outperforms all baselines in reasoning on emerging entities, achieving an average improvement of 28.6% in Mean Reciprocal Rank (MRR) across multiple datasets. The implementations are available at https://github.com/zhaodazhuang2333/TransFIR.