TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

TL;DR

TFLEX introduces a novel framework for multi-hop logical reasoning over temporal knowledge graphs, effectively handling temporal and logical operators to answer complex temporal queries.

Contribution

The paper presents the first temporal complex query embedding method, TFLEX, which models both entity and timestamp logic for reasoning over TKGs.

Findings

TFLEX outperforms existing methods on multiple query patterns.

It effectively models temporal operators like After, Before, and Between.

Experiments validate the framework's ability to answer complex temporal queries.

Abstract

Multi-hop logical reasoning over knowledge graph (KG) plays a fundamental role in many artificial intelligence tasks. Recent complex query embedding (CQE) methods for reasoning focus on static KGs, while temporal knowledge graphs (TKGs) have not been fully explored. Reasoning over TKGs has two challenges: 1. The query should answer entities or timestamps; 2. The operators should consider both set logic on entity set and temporal logic on timestamp set. To bridge this gap, we define the multi-hop logical reasoning problem on TKGs. With generated three datasets, we propose the first temporal CQE named Temporal Feature-Logic Embedding framework (TFLEX) to answer the temporal complex queries. We utilize vector logic to compute the logic part of Temporal Feature-Logic embeddings, thus naturally modeling all First-Order Logic (FOL) operations on entity set. In addition, our framework extends vector logic on timestamp set to cope with three extra temporal operators (After, Before and Between). Experiments on numerous query patterns demonstrate the effectiveness of our method.