![[2602.19569] Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.19569] Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering
Summary
This paper presents a novel framework for Temporal Question Answering over Temporal Knowledge Graphs, addressing limitations in temporal reasoning and representation fusion.
Why It Matters
As the demand for accurate temporal reasoning in AI applications grows, this research provides significant advancements in handling time-sensitive queries, which are crucial for various applications in natural language processing and knowledge representation.
Key Takeaways
- Introduces a constraint-aware question representation that integrates semantic cues and temporal dynamics.
- Develops a temporal-aware graph neural network for enhanced multi-hop reasoning.
- Implements a multi-view attention mechanism for effective fusion of question context and temporal graph knowledge.
- Demonstrates consistent improvements over existing benchmarks in Temporal Knowledge Graph Question Answering.
- Addresses common challenges in temporal reasoning, enhancing the accuracy of AI responses.
Computer Science > Computation and Language arXiv:2602.19569 (cs) [Submitted on 23 Feb 2026] Title:Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering Authors:Wuzhenghong Wen, Bowen Zhou, Jinwen Huang, Xianjie Wu, Yuwei Sun, Su Pan, Liang Li, Jianting Liu View a PDF of the paper titled Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering, by Wuzhenghong Wen and 7 other authors View PDF HTML (experimental) 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 con...