Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering

TL;DR

This paper introduces a novel framework for temporal question answering over knowledge graphs, integrating temporal-aware encoding, multi-hop reasoning, and multi-view fusion to improve reasoning accuracy.

Contribution

It presents a new approach combining temporal-aware question encoding, explicit multi-hop reasoning, and multi-view fusion, addressing limitations of previous methods.

Findings

Consistent improvements on TKGQA benchmarks

Enhanced multi-hop reasoning capabilities

More effective fusion of language and graph information

Abstract

Question Answering over Temporal Knowledge Graphs (TKGQA) has attracted growing interest for handling time-sensitive queries. However, existing methods still struggle with: 1) weak incorporation of temporal constraints in question representation, causing biased reasoning; 2) limited ability to perform explicit multi-hop reasoning; and 3) suboptimal fusion of language and graph representations. We propose a novel framework with temporal-aware question encoding, multi-hop graph reasoning, and multi-view heterogeneous information fusion. Specifically, our approach introduces: 1) a constraint-aware question representation that combines semantic cues from language models with temporal entity dynamics; 2) a temporal-aware graph neural network for explicit multi-hop reasoning via time-aware message passing; and 3) a multi-view attention mechanism for more effective fusion of question context and temporal graph knowledge. Experiments on multiple TKGQA benchmarks demonstrate consistent improvements over multiple baselines.