Temporal knowledge graph reasoning via multi-granularity knowledge refinement

Abstract

Temporal Knowledge Graph (TKG) reasoning plays a pivotal role in predicting emerging facts based on historical data. However, existing TKG reasoning methods typically aggregate all historical facts within a given time window indiscriminately, which often introduces outdated or irrelevant information. This information redundancy can significantly hinder the reasoning performance, especially as TKGs continue to grow in scale and complexity. Effectively filtering out irrelevant facts is thus essential for improving inference accuracy and efficiency. To address this critical challenge, we focus on how to refine the TKGs and propose a Temporal knowledge graph reasoning model via Multi-granularity Knowledge Refinement (T-MKR). Specifically, we propose a multi-granularity knowledge refinement approach to prune historical TKGs, which selectively removes irrelevant edges and unnecessary nodes at both the edge and node levels. The resulting refined subgraphs are used for representation learning. To effectively combine information from both refinements, we introduce a subgraph gating integration module. Additionally, we leverage contrastive learning for subgraph alignment to emphasize the relationships between the two refined subgraphs. Extensive experiments on six commonly used datasets demonstrate the superiority of T-MKR compared with many state-of-the-art baselines.

Graphical abstract

Keywords

temporal knowledge graph / temporal knowledge graph reasoning / knowledge refinement

References

[1] Zheng X L, Li P P, Zhang Z, Wu X D . RPND: a rule guided link prediction model with specific-path selection. Frontiers of Computer Science, 2026, 20( 1): 2001309

[2] Chen Y, Liu W, Wu X, Chen N, Zheng Z, Xu T, Chen E . A graph embedding-based dynamic update method for intelligence knowledge graphs. Frontiers of Computer Science, 2026, 20( 7): 2007337

[3] He T, Liu M, Cao Y, Wang Z, Zheng Z, Qin B . Exploiting high-order graph structure for sparse knowledge graph completion. Frontiers of Computer Science, 2025, 19( 2): 192306

[4] Dong B, Bu C, Zhu Y, Ji S, Wu X . Simplified multi-view graph neural network for multilingual knowledge graph completion. Frontiers of Computer Science, 2025, 19( 7): 197324

[5] Zhang Z, Guan Z P, Zhang F W, Zhuang F Z, An Z L, Wang F, Xu Y J. Weighted knowledge graph embedding. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2023, 867–877

[6] Zhang F, Zhang Z, Ao X, Gao D, Zhuang F, Wei Y, He Q. Mind the gap: cross-lingual information retrieval with hierarchical knowledge enhancement. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence. 2022, 4345–4353

[7] Xu C, Zhang F, Zhang Z, Zhuang F, Liu R. Exploring high-order user preference with knowledge graph for recommendation. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. 2024, 4138–4142

[8] Deng S, Rangwala H, Ning Y. Dynamic knowledge graph based multi-event forecasting. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020, 1585–1595

[9] Xu Y, Fu L Y, Wang X B . Rethinking temporal knowledge graph extrapolation: prioritizing historical events over graph. Frontiers of Computer Science, 2025, 19( 11): 1911366

[10] Liu J, Yu Z, Guo B, Deng C, Fu L, Wang X, Zhou C . EvolveKG: a general framework to learn evolving knowledge graphs. Frontiers of Computer Science, 2024, 18( 3): 183309

[11] Mavromatis C, Subramanyam P L, Ioannidis V N, Adeshina A, Howard P R, Grinberg T, Hakim N, Karypis G. TempoQR: temporal question reasoning over knowledge graphs. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence. 2022, 5825–5833

[12] Signorini A, Segre A M, Polgreen P M . The use of twitter to track levels of disease activity and public concern in the U. S. during the influenza a H1N1 pandemic. PLoS One, 2011, 6( 5): e19467

[13] Bollen J, Mao H, Zeng X . Twitter mood predicts the stock market. Journal of Computational Science, 2011, 2( 1): 1–8

[14] Jin W, Qu M, Jin X, Ren X. Recurrent event network: autoregressive structure inferenceover temporal knowledge graphs. In: Proceedings of 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020, 6669–6683

[15] Li Z, Jin X, Li W, Guan S, Guo J, Shen H, Wang Y, Cheng X. Temporal knowledge graph reasoning based on evolutional representation learning. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021, 408–417

[16] Zhu C, Chen M, Fan C, Cheng G, Zhang Y. Learning from history: modeling temporal knowledge graphs with sequential copy-generation networks. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021, 4732–4740

[17] Li Y, Sun S, Zhao J. TiRGN: time-guided recurrent graph network with local-global historical patterns for temporal knowledge graph reasoning. In: Proceedings of the 31st International Joint Conference on Artificial Intelligence. 2022, 2152–2158

[18] Liang K, Meng L, Liu M, Liu Y, Tu W, Wang S, Zhou S, Liu X, Sun F. Reasoning over different types of knowledge graphs: static, temporal and multi-modal. 2022, arXiv preprint arXiv: 2212.05767

[19] Dasgupta S S, Ray S N, Talukdar P. HyTE: hyperplane-based temporally aware knowledge graph embedding. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 2001–2011

[20] Wang Z, Zhang J, Feng J, Chen Z. Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. 2014, 1112–1119

[21] Ji G, Liu K, He S, Zhao J. Knowledge graph completion with adaptive sparse transfer matrix. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016, 985–991

[22] Goel R, Kazemi S M, Brubaker M, Poupart P. Diachronic embedding for temporal knowledge graph completion. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020, 3988–3995

[23] Balažević I, Allen C, Hospedales T. TuckER: tensor factorization for knowledge graph completion. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019, 5185–5194

[24] Trouillon T, Welbl J, Riedel S, Gaussier É, Bouchard G. Complex embeddings for simple link prediction. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning. 2016, 2071–2080

[25] Lacroix T, Obozinski G, Usunier N. Tensor decompositions for temporal knowledge base completion. In: Proceedings of the 8th International Conference on Learning Representations. 2019

[26] Zhang F, Zhang Z, Ao X, Zhuang F, Xu Y, He Q. Along the time: timeline-traced embedding for temporal knowledge graph completion. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022, 2529–2538

[27] Chen K, Wang Y, Li Y, Li A. RotateQVS: representing temporal information as rotations in quaternion vector space for temporal knowledge graph completion. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022, 5843–5857

[28] Zhang F, Zhang Z, Zhuang F, Zhao Y, Wang D, Zheng H . Temporal knowledge graph reasoning with dynamic memory enhancement. IEEE Transactions on Knowledge and Data Engineering, 2024, 36( 11): 7115–7128

[29] Zhang F, Zhang Z, Zhuang F, Zhang Z, Zhou J, Wang D. Multi-view temporal knowledge graph reasoning. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. 2024, 4263–4267

[30] Han Z, Ding Z, Ma Y, Gu Y, Tresp V. Learning neural ordinary equations for forecasting future links on temporal knowledge graphs. In: Proceedings of 2021 Conference on Empirical Methods in Natural Language Processing. 2021, 8352–8364

[31] Sun H, Zhong J, Ma Y, Han Z, He K. TimeTraveler: reinforcement learning for temporal knowledge graph forecasting. In: Proceedings of 2021 Conference on Empirical Methods in Natural Language Processing. 2021, 8306–8319

[32] Zheng S, Yin H, Chen T, Nguyen Q V H, Chen W, Zhao L. DREAM: adaptive reinforcement learning based on attention mechanism for temporal knowledge graph reasoning. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2023, 1578–1588

[33] Han Z, Chen P, Ma Y, Tresp V. xERTE: explainable reasoning on temporal knowledge graphs for forecasting future links. 2020, arXiv preprint arXiv: 2012.15537

[34] Li Z, Guan S, Jin X, Peng W, Lyu Y, Zhu Y, Bai L, Li W, Guo J, Cheng X. Complex evolutional pattern learning for temporal knowledge graph reasoning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2022, 290–296

[35] Xia Y, Wang D, Liu Q, Wang L, Wu S, Zhang X. Chain-of-history reasoning for temporal knowledge graph forecasting. In: Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024. 2024, 16144–16159

[36] Leblay J, Chekol M W. Deriving validity time in knowledge graph. In: Companion Proceedings of the the Web Conference 2018. 2018, 1771–1776

[37] Bordes A, Usunier N, Garcia-Durán A, Weston J, Yakhnenko O. Translating embeddings for modeling multi-relational data. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. 2013, 2787–2795

[38] García-Durán A, Dumančić S, Niepert M. Learning sequence encoders for temporal knowledge graph completion. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 4816–4821

[39] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. 2017

[40] Schlichtkrull M S, Kipf T N, Bloem P, Van Den Berg R, Titov I, Welling M. Modeling relational data with graph convolutional networks. In: Proceedings of the 15th International Conference on the Semantic Web. 2018, 593–607

[41] Cho K, Van Merriënboer B, Bahdanau D, Bengio Y. On the properties of neural machine translation: Encoder–decoder approaches. In: Proceedings of the 8th Workshop on Syntax, Semantics and Structure in Statistical Translation. 2014, 103–111

[42] Zhang M Q, Xia Y W, Liu Q, Wu S, Wang L. Learning long- and short-term representations for temporal knowledge graph reasoning. In: Proceedings of the ACM Web Conference 2023. 2023, 2412–2422

[43] Xiao Y, Zhou G, Xie Z, Liu J, Huang J X . Learning dual disentangled representation with self-supervision for temporal knowledge graph reasoning. Information Processing & Management, 2024, 61( 3): 103618

[44] Liang K, Meng L, Liu M, Liu Y, Tu W, Wang S, Zhou S, Liu X. Learn from relational correlations and periodic events for temporal knowledge graph reasoning. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2023, 1559–1568

[45] Huang R, Wei W, Qu X, Zhang S, Chen D, Cheng Y. Confidence is not timeless: Modeling temporal validity for rule-based temporal knowledge graph forecasting. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024, 10783–10794

[46] Chen W, Wu Y, Wu S, Zhang Z, Liao M, Lin Y, Wan H. CognTKE: a cognitive temporal knowledge extrapolation framework. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence. 2025, 1651

[47] Rendle S, Freudenthaler C, Gantner Z, Schmidt-Thieme L. BPR: Bayesian personalized ranking from implicit feedback. In: Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. 2009, 452–461

[48] Shang C, Tang Y, Huang J, Bi J, He X, Zhou B. End-to-end structure-aware convolutional networks for knowledge base completion. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019, 3060–3067

[49] Vrandečić D, Krötzsch M . Wikidata: a free collaborative knowledgebase. Communications of the ACM, 2014, 57( 10): 78–85

[50] Suchanek F M, Kasneci G, Weikum G. Yago: a core of semantic knowledge. In: Proceedings of the 16th International Conference on World Wide Web. 2007, 697–706

[51] Kingma D P, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations. 2015

Rights & permissions

Higher Education Press