Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

2026-04-11

AI Summary

Existing approaches to temporal knowledge graph reasoning are constrained by the closed-world assumption, rendering them ineffective for reasoning about emerging entities unseen during training. To address this limitation, this work proposes TransFIR, a novel framework that integrates semantic clustering with transferable temporal interaction patterns to enable inductive reasoning over emerging entities. By transferring historical behavioral patterns from semantically similar known entities, TransFIR facilitates effective inference even in the absence of prior interactions. The method incorporates a codebook-based classifier and a temporal knowledge graph embedding mechanism, achieving an average MRR improvement of 28.6% across multiple benchmark datasets. This substantial gain over current baselines demonstrates the framework’s efficacy in tackling the challenging problem of reasoning about new entities lacking historical interaction records.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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.

Problem

• Temporal Knowledge Graphs
• Emerging Entities
• Inductive Reasoning
• Closed-world Assumption
• Entity Interaction

Innovation

• inductive reasoning
• temporal knowledge graphs
• emerging entities
• transferable patterns
• semantic clustering