Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning

TL;DR

This paper introduces a strikingness-aware evaluation framework for temporal knowledge graph reasoning, emphasizing the importance of predicting rare, outstanding events over trivial repetitions.

Contribution

It proposes a rule-based strikingness measuring framework and integrates it into evaluation metrics, improving the assessment of reasoning models on significant events.

Findings

All models perform worse on high-strikingness events.

Path-based models excel on low-strikingness events.

Ensemble methods tend to fit trivial events rather than reasoning.

Abstract

Temporal Knowledge Graph Reasoning (TKGR) aims at inferring missing (especially future) events from historical data. Current evaluation in TKGR uniformly weights all events, ignoring that most are trivial repetitions, which overestimate the true reasoning ability. Therefore, the rare outstanding events, whose prediction demands deeper reasoning, should be distinguished and emphasized. To this end, we propose a strikingness-aware evaluation framework, which introduces a rule-based strikingness measuring framework (RSMF) to quantify event strikingness by comparing its expected occurrence with peer events derived from temporal rules. Strikingness is then integrated as a weighting factor into metrics like weighted MRR and Hits@k. Experiments on four TKG benchmarks reveal: 1) All representative models perform worse as event strikingness increases, 2) Path-based methods excel on low-strikingness events and representation-based ones on high-strikingness events, 3) We design an ensemble method whose gains stem from fitting trivial events rather than reasoning improvement. Our framework provides a more rigorous evaluation, refocusing the field on predicting outstanding events.