[Objective] This paper tries to address the issues of incomplete entity information extraction and importance measurement of different timestamps for the events to be reasoned in temporal knowledge graph. [Methods] We proposed a new model based on entity multiple unit coding(EMUC). The EMUC introduces the entity slice feature encodings for the current timestamps, the entity dynamic feature encodings fusing timestamp embedding and entity static features, as well as entity segment feature encodings over historical steps. We also utilized a temporal attention mechanism to learn the importance weights of local structural information at different timestamps to the inference target. [Results] The experimental results of the proposed model on the ICEWS14 test set were MRR: 0.470 4, Hits@1: 40.31%, Hits@3: 50.02%, Hits@10: 59.98%, while on the ICEWS18 test set were MRR: 0.438 5, Hits@1: 37.55%, Hits@3: 46.92%, Hits@10: 56.85%, and on the YAGO test set are MRR: 0.656 4, Hits@1: 63.07%, Hits@3 : 65.87%, Hits@10: 68.37%. Our model outperforms the existing methods on these evaluating metrics. [Limitations] EMUC has slow inference speed for large-scale datasets. [Conclusions] The newly temporal attention mechanism measures the importance of historical local structure information for reasoning, which effectively improves the reasoning performance of the temporal knowledge graph.
Bordes A, Usunier N, García-Durán A, et al. Translating Embeddings for Modeling Multi-Relational Data[C]// Proceedings of the 2013 Conference and Workshop on Neural Information Processing Systems. 2013: 2787-2795.
[2]
Yang B S, Yih S W, He X D, et al. Learning Multi-Relational Semantics Using Neural-Embedding Models[C]// Proceedings of the 2014 Conference and Workshop on Neural Information Processing Systems. 2014.
[3]
Trouillon T, Welbl J, Riedel S, et al. Complex Embeddings for Simple Link Prediction[C]// Proceedings of the 2016 International Conference on Machine Learning. 2016: 2071-2080.
[4]
Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling Relational Data with Graph Convolutional Networks[C]// Proceedings of the 2018 European Semantic Web Symposium. 2018: 593-607.
[5]
Zhang W, Paudel B, Wang L, et al. Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning[C]// Proceedings of the 2019 World Wide Web Conference. 2019: 2366-2377.
( Ruan Xiaoyun, Liao Jianbin, Li Xiang, et al. Interpretable Recommendation of Reinforcement Learning Based on Talent Knowledge Graph Reasoning[J]. Data Analysis and Knowledge Discovery, 2021, 5(6): 36-50.)
( Zhu Chaoyu, Liu Lei. A Review of Medical Decision Supports Based on Knowledge Graph[J]. Data Analysis and Knowledge Discovery, 2020, 4(12): 26-32.)
[8]
Leblay J, Chekol M W. Deriving Validity Time in Knowledge Graph[C]// Proceedings of the 2018 World Wide Web Conference. 2018: 1771-1776.
[9]
García-Durán A, Dumančić S, Niepert M. Learning Sequence Encoders for Temporal Knowledge Graph Completion[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018: 4816-4821.
[10]
Goel R, Kazemi S M, Brubaker M, et al. Diachronic Embedding for Temporal Knowledge Graph Completion[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020: 3988-3995.
[11]
Lacroix T, Obozinski G, Usunier N. Tensor Decompositions for Temporal Knowledge Base Completion[C]// Proceedings of the 8th International Conference on Learning Representations. 2020.
[12]
Jin W, Qu M, Jin X S, et al. Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 6669-6683.
( Chen Hao, Li Yongqiang, Feng Yuanjing, Dynamic Knowledge Graph Inference Based on Multiple Relational Cyclic Events[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(4): 337-343.)
doi: 10.16451/j.cnki.issn1003-6059.202004006
[14]
Wu J P, Cao M, Cheung J C K, et al. TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 5730-5746.
[15]
Han Z, Chen P, Ma Y, et al. Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs[C]// Proceedings of the 2021 International Conference on Learning Representations. 2021.
[16]
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. 2021: 408-417.
[17]
Liu Y S, Ma Y P, Hildebrandt M, et al. TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs[C]// Proceedings of the 36th AAAI Conference on Artificial Intelligence. 2022: 4120-4127.
[18]
Boschee E, Lautenschlager J, O’Brien S, et al. ICEWS Coded Event Data[OL]. Harvard Dataverse, 2015. https://doi.org/10.7910/DVN/28075.
[19]
Mahdisoltani F, Biega J A, Suchanek F M.YAGO3: A Knowledge Base from Multilingual Wikipedias[C]// Proceedings of the 2014 Conference on Innovative Data Systems Research. 2014.
[20]
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 35th AAAI Conference on Artificial Intelligence. 2021: 4732-4740.
[21]
Bai L Y, Yu W T, Chen M Z, et al. Multi-Hop Reasoning over Paths in Temporal Knowledge Graphs Using Reinforcement Learning[J]. Applied Soft Computing, 2021, 103: 107144.
doi: 10.1016/j.asoc.2021.107144
[22]
Pareja A, Domeniconi G, Chen J, et al. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020.
