基于联合卷积的时序知识图谱推理

doi:10.3778/j.issn.1002-8331.2406-0236

摘要/Abstract

摘要： 针对现有时序知识图谱推理模型不能充分挖掘时序知识图谱中并发事实的结构依赖和潜在关系，时间编码方式单一不合理，获取时间信息单调的问题。提出了一种基于联合卷积的时序知识图谱推理模型。该模型一方面通过引入使用联合聚合器的图卷积神经网络挖掘节点邻域信息的表面语义和潜在特征；另一方面，通过对时间进行向量编码和事件属性编码来捕获丰富的时间信息，增强模型的时间敏感性。在ICEWS14、ICEWS05-15、YAGO和GDELT数据集上的实验结果表明，模型在MRR、Hits@1、Hits@3和Hits@10上普遍优于基线模型，同时关系预测也均优于基线模型。

关键词: 时序知识图谱, 图卷积神经网络, 门控循环单元, 联合卷积

Abstract: Existing temporal knowledge graph reasoning models fail to fully explore the structural dependencies and potential relationships among concurrent facts in temporal knowledge graphs. Additionally, these models often rely on simplistic and unreasonable time encoding methods, resulting in inadequate temporal information acquisition. This paper proposes a temporal knowledge graph reasoning model based on joint convolution. This model uses a joint aggregator in a graph convolutional neural network to capture the surface semantics and latent features of node neighborhood information. It also employs vector and event attribute encoding for time to capture rich temporal information, enhancing the temporal sensitivity of the model. Experimental results on ICEWS14, ICEWS05-15, YAGO, and GDELT datasets demonstrate that the model consistently outperforms baseline models in MRR, Hits@1, Hits@3, and Hits@10, as well as in relation prediction.

Key words: temporal knowledge graph, graph convolutional network, gated recurrent unit, joint convolution

张成珅, 马汉达. 基于联合卷积的时序知识图谱推理[J]. 计算机工程与应用, 2025, 61(18): 166-174.

ZHANG Chengshen, MA Handa. Temporal Knowledge Graph Reasoning Based on Joint Convolution[J]. Computer Engineering and Applications, 2025, 61(18): 166-174.

参考文献

[1] WU X H, DUAN J W, PAN Y, et al. Medical knowledge graph: data sources, construction, reasoning, and applications[J]. Big Data Mining and Analytics, 2023, 6(2): 201-217.
[2] CHEN Z, WANG Y H, ZHAO B, et al. Knowledge graph completion: a review[J]. IEEE Access, 2020, 8: 192435-192456.
[3] PENG C Y, XIA F, NASERIPARSA M, et al. Knowledge graphs: opportunities and challenges[J]. Artificial Intelligence Review, 2023, 56(11): 13071-13102.
[4] LIANG K, MENG L Y, LIU M, et al. A survey of knowledge graph reasoning on graph types: static, dynamic, and multi-modal[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 9456-9478.
[5] MA M B, XIE P, TENG F, et al. HiSTGNN: hierarchical spatio-temporal graph neural network for weather forecasting[J]. Information Sciences, 2023, 648: 119580.
[6] 吴国栋, 王雪妮, 刘玉良. 知识图谱增强的图神经网络推荐研究进展[J]. 计算机工程与应用, 2023, 59(4): 18-29.
WU G D, WANG X N, LIU Y L. Research advances on graph neural network recommendation of knowledge graph enhancement[J]. Computer Engineering and Applications, 2023, 59(4): 18-29.
[7] TAO M Y, GAO S S, MAO D Q, et al. Knowledge graph and deep learning combined with a stock price prediction network focusing on related stocks and mutation points[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(7): 4322-4334.
[8] ASMARA S M, SAHABUDIN N A, NADIAH ISMAIL N S, et al. A review of knowledge graph embedding methods of TransE, TransH and TransR for missing links[C]//Proceedings of the 2023 IEEE 8th International Conference on Software Engineering and Computer Systems. Piscataway: IEEE, 2023: 470-475.
[9] HU B J, YE Y Q, ZHONG Y Q, et al. TransMKR: translation-based knowledge graph enhanced multi-task point-of-interest recommendation[J]. Neurocomputing, 2022, 474: 107-114.
[10] BHATTI U A, TANG H, WU G L, et al. Deep learning with graph convolutional networks: an overview and latest applications in computational intelligence[J]. International Journal of Intelligent Systems, 2023, 2023(1): 8342104.
[11] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the European Semantic Web Conference. Cham: Springer, 2018: 593-607.
[12] VASHISHTH S, SANYAL S, NITIN V, et al. Composition-based multi-relational graph convolutional networks[J]. arXiv:1911.03082, 2019.
[13] MO X Y, HUANG Z Y, XING Y, et al. Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 9554-9567.
[14] 肖蕾, 李琪. 时序知识图谱补全方法研究综述[J]. 计算机工程与应用, 2024, 60(6): 43-54.
XIAO L, LI Q. Survey of temporal knowledge graph completion methods[J]. Computer Engineering and Applications, 2024, 60(6): 43-54.
[15] JIANG T, LIU T, GE T, et al. Towards time-aware knowledge graph completion[C]//Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2016: 1715-1724.
[16] LACROIX T, OBOZINSKI G, USUNIER N. Tensor decompositions for temporal knowledge base completion[J]. arXiv:2004.04926, 2020.
[17] BAI L Y, MA X N, MENG X X, et al. RoAN: a relation-oriented attention network for temporal knowledge graph completion[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106308.
[18] NIE H J, ZHAO X G, YAO X, et al. Temporal-structural importance weighted graph convolutional network for temporal knowledge graph completion[J]. Future Generation Computer Systems, 2023, 143: 30-39.
[19] TRIVEDI R, DAI H, WANG Y, et al. Know-evolve: deep temporal reasoning for dynamic knowledge graphs[C]//Proceedings of the International Conference on Machine Learning, 2017: 3462-3471.
[20] TRIVEDI R, FARAJTABAR M, BISWAL P, et al. DyREP: learning representations over dynamic graphs[C]//Proceedings of the International Conference on Learning Representations, 2019.
[21] DENG S, RANGWALA H, NING Y. Dynamic knowledge graph based multi-event forecasting[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2020: 1585-1595.
[22] JIN W, QU M, JIN X, et al. Recurrent event network: autoregressive structure inference over temporal knowledge graphs[J]. arXiv:1904.05530, 2019.
[23] LI Z X, JIN X L, LI W, et al. Temporal knowledge graph reasoning based on evolutional representation learning[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2021: 408-417.
[24] LI Z, GUAN S, JIN X, et al. Complex evolutional pattern learning for temporal knowledge graph reasoning[J]. arXiv:2203.07782, 2022.
[25] HAN Z, DING Z F, MA Y P, et al. Learning neural ordinary equations for forecasting future links on temporal knowledge graphs[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2021: 8352-8364.
[26] HAN Z, CHEN P, MA Y P, et al. Explainable subgraph reasoning for forecasting on temporal knowledge graphs[C]//Proceedings of the International Conference on Learning Representations, 2020.
[27] ZHU C C, CHEN M H, FAN C J, et al. Learning from history: modeling temporal knowledge graphs with sequential copy-generation networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021: 4732-4740.
[28] LI Y J, SUN S L, ZHAO J. TiRGN: time-guided recurrent graph network with local-global historical patterns for temporal knowledge graph reasoning[C]//Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022: 2152-2158.
[29] LI Z, HOU Z, GUAN S, et al. Hismatch: historical structure matching based temporal knowledge graph reasoning[J]. arXiv:2210.09708, 2022.
[30] LIU K Z, ZHAO F, XU G D, et al. RETIA: relation-entity twin-interact aggregation for temporal knowledge graph extrapolation[C]//Proceedings of the 2023 IEEE 39th International Conference on Data Engineering. Piscataway: IEEE, 2023: 1761-1774.
[31] XU Y, OU J J, XU H, et al. Temporal knowledge graph reasoning with historical contrastive learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2023: 4765-4773.
[32] WANG Y C, GUO S, GUO J C, et al. Towards performance-maximizing neural network pruning via global channel attention[J]. Neural Networks, 2024, 171: 104-113.
[33] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[34] VASHISHTH S, SANYAL S, NITIN V, et al. InteractE: improving convolution?based knowledge graph embeddings by increasing feature interactions[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 3009-3016.
[35] GAO R. Rethinking dilated convolution for real-time semantic segmentation[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2023: 4675-4684.
[36] JUNG J, JUNG J H, KANG U. Learning to walk across time for interpretable temporal knowledge graph completion[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York: ACM, 2021: 786-795.
[37] SEO Y, DEFFERRARD M, VANDERGHEYNST P, et al. Structured sequence modeling with graph convolutional recurrent networks[C]//Proceedings of the 25th International Conference on Neural Information Processing. Cham: Springer, 2018: 362-373.