Lune

EMNLP Findings2023

TR-Rules: Rule-based Model for Link Forecasting on Temporal Knowledge Graph Considering Temporal Redundancy

Ningyuan Li, Haihong E, Shi Li, Mingzhi Sun, Tianyu Yao, Meina Song, Yong Wang, Haoran Luo

Abstract

Temporal knowledge graph (TKG) has been proved to be an effective way for modeling dynamic facts in real world. Many efforts have been devoted into predicting future events i.e. extrapolation, on TKGs. Recently, rule-based knowledge graph completion methods which are considered to be more interpretable than embedding-based methods, have been transferred to temporal knowledge graph extrapolation. However, rule-based models suffer from temporal redundancy when leveraged under dynamic settings, which results in inaccurate rule confidence calculation. In this paper, we define the problem of temporal redundancy and propose TR-Rules which solves the temporal redundancy issues through a simple but effective strategy. Besides, to capture more information lurking in TKGs, apart from cyclic rules, TR-Rules also mines and properly leverages acyclic rules, which has not been explored by existing models. Experimental results on three benchmarks show that TR-Rules achieves stateof-the-art performance. Ablation study shows the impact of temporal redundancy and demonstrates the performance of acyclic rules is much more promising due to its higher sensitivity to the number of sampled walks during learning stage. 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.

3 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 Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs
  • 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
  • INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph cites Tensor Decompositions for Temporal Knowledge Base Completion
  • INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph cites Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs
  • INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph cites Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting
  • 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
  • Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
  • Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
  • Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting cites Diachronic Embedding for Temporal Knowledge Graph Completion
  • Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting cites Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph ForecastingRikui Huang, Wei Wei, Xiaoye Qu, Shengzhe Zhang et al.ACL 2024 · 7 citations
  2. 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
  3. INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge GraphNingyuan Li, Haihong E, Tianyu Yao, Tianyi Hu et al.ICLR 2025

Builds on8

  1. Diachronic Embedding for Temporal Knowledge Graph CompletionRishab Goel, Seyed Mehran Kazemi, Marcus A. Brubaker, Pascal PoupartAAAI 2020 · 423 citations
  2. Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge GraphsWoojeong Jin, Meng Qu, Xisen Jin, Xiang RenEMNLP 2020 · 353 citations
  3. 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
  4. Tensor Decompositions for Temporal Knowledge Base CompletionTimothée Lacroix, Guillaume Obozinski, Nicolas UsunierICLR 2020 · 341 citations
  5. Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge GraphsZhen Han, Peng Chen, Yunpu Ma, Volker TrespICLR 2021 · 213 citations

Related papers

  1. Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge GraphZhongwu Chen, Chengjin Xu, Fenglong Su, Zhen Huang et al.WWW 2023 · 18 citations
  2. An Adaptive Logical Rule Embedding Model for Inductive Reasoning over Temporal Knowledge GraphsXin Mei, Libin Yang, Xiaoyan Cai, Zuowei JiangEMNLP 2022 · 12 citations
  3. Re-Temp: Relation-Aware Temporal Representation Learning for Temporal Knowledge Graph CompletionKunze Wang, Soyeon Caren Han, Josiah PoonEMNLP Findings 2023 · 17 citations
  4. A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and ExtrapolationKai Chen, Ye Wang, Yitong Li, Aiping Li et al.ACL 2024 · 4 citations
  5. TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge GraphsYushan Liu, Yunpu Ma, Marcel Hildebrandt, Mitchell Joblin et al.AAAI 2022 · 193 citations
Dusk over the sea between two cliffs drawn in fine vertical lines