Lune

EMNLP Findings2022

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

Abstract

A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (subject, relation, object, timestamp) to describe dynamic facts. TKG reasoning has facilitated many real-world applications via answering such queries as (query entity, query relation, ?, future timestamp) about future. This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps. In addition, recent KGs provide background knowledge of all the entities, which is also helpful for the matching. Thus, in this paper, we propose the Historical Structure Matching (HiSMatch) model. It applies two structure encoders to capture the semantic information contained in the historical structures of the query and candidate entities. Besides, it adopts another encoder to integrate the background knowledge into the model. TKG reasoning experiments on six benchmark datasets demonstrate the significant improvement of the proposed HiSMatch model, with up to 5.6% performance improvement in MRR, compared to the state-of-the-art baselines. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

9 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning
  • Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning cites Composition-based Multi-Relational Graph Convolutional Networks
  • Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning cites Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning
  • Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks cites Tensor Decompositions for Temporal Knowledge Base Completion
  • Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • Tensor Decompositions for Temporal Knowledge Base Completion cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs cites Tensor Decompositions for Temporal Knowledge Base Completion
  • Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning cites Tensor Decompositions for Temporal Knowledge Base Completion
  • DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • Context-aware Event Forecasting via Graph Disentanglement cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • Context-aware Event Forecasting via Graph Disentanglement cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • Context-aware Event Forecasting via Graph Disentanglement cites Composition-based Multi-Relational Graph Convolutional Networks
  • Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning cites Tensor Decompositions for Temporal Knowledge Base Completion
  • Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning cites Composition-based Multi-Relational Graph Convolutional Networks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers9

  1. Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph ReasoningWei Chen, Huaiyu Wan, Yuting Wu, Shuyuan Zhao et al.ICDE 2024 · 42 citations
  2. DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph ReasoningShangfei Zheng, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen et al.SIGIR 2023 · 27 citations
  3. Context-aware Event Forecasting via Graph DisentanglementYunshan Ma, Chenchen Ye, Zijian Wu, Xiang Wang et al.KDD 2023 · 10 citations
  4. LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge GraphsKai Chen, Xin Song, Ye Wang, Liqun Gao et al.AAAI 2025 · 6 citations
  5. Historically Relevant Event Structuring for Temporal Knowledge Graph ReasoningJinchuan Zhang, Ming Sun, Chong Mu, Jinhao Zhang et al.ICDE 2025 · 4 citations

Builds on12

  1. Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 citations
  2. Diachronic Embedding for Temporal Knowledge Graph CompletionRishab Goel, Seyed Mehran Kazemi, Marcus A. Brubaker, Pascal PoupartAAAI 2020 · 423 citations
  3. Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge GraphsWoojeong Jin, Meng Qu, Xisen Jin, Xiang RenEMNLP 2020 · 353 citations
  4. Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation NetworksCunchao Zhu, Muhao Chen, Changjun Fan, Guangquan Cheng et al.AAAI 2021 · 343 citations
  5. Tensor Decompositions for Temporal Knowledge Base CompletionTimothée Lacroix, Guillaume Obozinski, Nicolas UsunierICLR 2020 · 341 citations

Related papers

  1. Learning to Walk across Time for Interpretable Temporal Knowledge Graph CompletionJaehun Jung, Jinhong Jung, U KangKDD 2021 · 93 citations
  2. Multi-Granularity History and Entity Similarity Learning for Temporal Knowledge Graph ReasoningShi Mingcong, Chunjiang Zhu, Detian Zhang, Shiting Wen et al.EMNLP 2024 · 4 citations
  3. Temporal Fact Reasoning over Hyper-Relational Knowledge GraphsZifeng Ding, Jingcheng Wu, Jingpei Wu, Yan Xia et al.EMNLP Findings 2024 · 1 citation
  4. A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge GraphsYimin Deng, Yuxia Wu, Yejing Wang, Guoshuai Zhao et al.ACL Findings 2025 · 3 citations
  5. Unsupervised Entity Alignment for Temporal Knowledge GraphsXiaoze Liu, Junyang Wu, Tianyi Li, Lu Chen et al.WWW 2023 · 56 citations
Dusk over the sea between two cliffs drawn in fine vertical lines