TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning

TL;DR

TEILP is a logical reasoning framework for time prediction in temporal knowledge graphs that captures temporal relationships more effectively than embedding-based models, providing interpretable results especially in limited data scenarios.

Contribution

We introduce TEILP, a novel logical reasoning approach that explicitly models temporal relationships in knowledge graphs for improved time prediction accuracy.

Findings

TEILP outperforms state-of-the-art methods on five benchmark datasets.

TEILP provides interpretable explanations for predictions.

TEILP is robust in scenarios with limited training data and imbalanced event types.

Abstract

Conventional embedding-based models approach event time prediction in temporal knowledge graphs (TKGs) as a ranking problem. However, they often fall short in capturing essential temporal relationships such as order and distance. In this paper, we propose TEILP, a logical reasoning framework that naturally integrates such temporal elements into knowledge graph predictions. We first convert TKGs into a temporal event knowledge graph (TEKG) which has a more explicit representation of time in term of nodes of the graph. The TEKG equips us to develop a differentiable random walk approach to time prediction. Finally, we introduce conditional probability density functions, associated with the logical rules involving the query interval, using which we arrive at the time prediction. We compare TEILP with state-of-the-art methods on five benchmark datasets. We show that our model achieves a significant improvement over baselines while providing interpretable explanations. In particular, we consider several scenarios where training samples are limited, event types are imbalanced, and forecasting the time of future events based on only past events is desired. In all these cases, TEILP outperforms state-of-the-art methods in terms of robustness.