Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning

TL;DR

This paper introduces LogCL, a contrastive learning approach that effectively fuses local and global historical information for temporal knowledge graph reasoning, improving robustness and predictive accuracy.

Contribution

It proposes a novel entity-aware attention mechanism and four contrast patterns to enhance historical information encoding and noise resistance in TKG reasoning.

Findings

LogCL outperforms state-of-the-art methods on four benchmarks.

The model demonstrates improved robustness against noisy inputs.

Entity-aware attention effectively captures query-related historical facts.

Abstract

Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant practical value across diverse fields. Most extrapolation studies in TKGs focus on modeling global historical fact repeating and cyclic patterns, as well as local historical adjacent fact evolution patterns, showing promising performance in predicting future unknown facts. Yet, existing methods still face two major challenges: (1) They usually neglect the importance of historical information in KG snapshots related to the queries when encoding the local and global historical information; (2) They exhibit weak anti-noise capabilities, which hinders their performance when the inputs are contaminated with noise.To this end, we propose a novel \blue{Lo}cal-\blue{g}lobal history-aware \blue{C}ontrastive \blue{L}earning model (\blue{LogCL}) for TKG reasoning, which adopts contrastive learning to better guide the fusion of local and global historical information and enhance the ability to resist interference. Specifically, for the first challenge, LogCL proposes an entity-aware attention mechanism applied to the local and global historical facts encoder, which captures the key historical information related to queries. For the latter issue, LogCL designs four historical query contrast patterns, effectively improving the robustness of the model. The experimental results on four benchmark datasets demonstrate that LogCL delivers better and more robust performance than the state-of-the-art baselines.