为了更加智能化地实现国家电网公司设计的公共数据模型（SG-CIM）的业务需求和提高图谱数据本身的质量和共享程度，提出一种基于图注意力网络的图结构映射模型。首先基于SG-CIM模型的数据构建SG-CIM模型知识图谱和数据库表知识图谱，然后通过图注意力网络分别学习每个图中的实体嵌入，将实体嵌入统一向量空间，最后基于实体向量之间的距离计算相似度，得到2个图的图结构映射结果。实验表明，本文提出的模型在SG-CIM数据模型自动映射方面得到相当不错的结果。
In order to intelligently meet the business requirements of the SG-CIM model designed by the State Grid Corporation of China and improve the quality and sharing of the graph data, this paper proposes a graph structure mapping model based on gaph attention network(GAT). First of all, using the data of SG-CIM model, an SG-CIM knowledge graph and a database table knowledge graph are constructed. The entities embedding in each graph are learned separately through the GAN, which are then embeded into a unified vector space. Finally, the graph structure mapping results of the two graphs are obtained after calculating the similarities based on the distances between the entity vectors. Experiments show that the proposed model achieves good results in automatic mapping of SG-CIM model.
[1] 万齐鸣, 王思宁, 何鑫. 数据中台SG-CIM模型应用方法[J]. 电信科学, 2020, 36(3): 136-143.
[2] Cao Y X, Liu Z Y, Li C J, et al. Multi-channel graph neural network for entity alignment[DB/OL]. arXiv preprint: 1908.09898, 2019.
[3] Chen M H, Tian Y T, Yang M H, et al. Multilingual knowledge graph embeddings for cross-lingual knowledge alignment[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. New York: ACM, 2017: 1511-1517.
[4] Sun Z Q, Hu W, Li C K. Cross-lingual entity alignment via joint attribute-preserving embedding[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2017: 628-644.
[5] Hao Y C, Zhang Y Z, He S Z, et al. A joint embedding method for entity alignment of knowledge bases[C]//Chen H, Ji H, Sun L, et al. Knowledge Graph and Semantic Computing: Semantic, Knowledge, and Linked Big Data. CCKS 2016. Communications in Computer and Information Science. Singapore: Springer, 2016, 650: 3-14.
[6] Zhu H, Xie R B, Liu Z Y, et al. Iterative entity alignment via joint knowledge embeddings[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. New York: ACM, 2017: 4258-4264.
[7] Wang Z C, Lv Q S, Lan X H, et al. Cross-lingual knowledge graph alignment via graph convolutional networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2018: 349-357.
[8] Veličković P, Cucurull G, Casanova A, et al. Graph attention networks[DB/OL]. arXiv preprint: 1710.10903, 2017.
[9] 徐有为, 张宏军, 程恺, 等 . 知识图谱嵌入研究综述[J].计算机工程与应用, 2022, 58(9): 30-50.
[10] Xu K, Wang L W, Yu M, et al. Cross-lingual knowledge graph alignment via graph matching neural network[DB/OL]. arXiv preprint: 1905.11605, 2019.
[11] Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks[DB/OL]. arXiv preprint: 1703.06103, 2017.
[12] Mao X, Wang W T, Wu Y B, et al. From alignment to assignment: Frustratingly simple unsupervised entity alignment[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2021: 2843–2853.
[13] 张富, 杨琳艳, 李健伟, 等. 实体对齐研究综述[J]. 计算机学报, 2022, 45(6): 1195-1225.
[14] 车超, 刘迪 . 基于双向对齐与属性信息的跨语言实体对齐[J]. 计算机工程, 2022, 48(3): 74-80.
[15] Nathani D, Chauhan J, Sharma C, et al. Learning attention-based embeddings for relation prediction in knowledge graphs[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2019: 4710-4723.
[16] 赵丹, 张俊 . 基于双重注意力和关系语义建模的实体对齐方法[J]. 计算机应用研究, 2022, 39(1): 64-69, 79.
[17] Wu Y T, Liu X, Feng Y S, et al. Relation-aware entity alignment for heterogeneous knowledge graphs[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2019: 5278-5284.
