计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 235-243.doi: 10.11896/jsjkx.221200097
孙首男, 汪璟玢, 吴仁飞, 游常凯, 柯禧帆, 黄皓
SUN Shounan, WANG Jingbin, WU Renfei, YOU Changkai, KE Xifan, HUANG Hao
摘要： 近年来利用图结构来解决知识图补全(KGC)问题取得了不错的进展,其中图神经网络(GNNs)通过聚合实体的局部邻域信息来不断更新中心实体的表示,图注意力网络(GATs)使用注意力机制有侧重地聚合邻居,以获得更准确的中心实体表示。这些模型虽然在KGC中取得了不错的性能,但它们都忽略了中心实体的类型信息,仅仅使用邻域信息来计算注意力,将导致计算出来的注意力不够精准。针对这些问题,文中提出了一种类型匹配约束的图注意力网络(TMGAT),该方法通过计算中心实体类型对每个邻域关系的注意力,来得到实体类型-关系级别的注意力,以进一步计算出中心实体与各邻域关系的类型匹配度,再通过邻域关系及对应的邻居实体,结合类型匹配度计算实体-关系级别的注意力,得到邻域节点对中心实体的最终注意力。使用类型匹配度来约束传统的注意力机制,提升注意力机制的准确性,得到更加精准的中心实体嵌入,进而提升知识图补全的准确性。截至目前,文中提出的TMGAT是第一个在GATs中结合显式类型进行知识图补全任务的模型。文中加工了两个现有的数据集,使数据集中每个实体都拥有若干个类型,以验证TMGAT模型的性能。最后,实验部分展现了TMGAT在知识补全任务中优秀的竞争力,并研究了类型个数对模型性能的影响。
中图分类号:
| [1]BOLLACKER K,EVANS C,PARITOSH P,et al.Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data.2008:1247-1250. [2]MILLER G A.WordNet:a lexical database for English[J].Communications of the ACM,1995,38(11):39-41. [3]SUCHANEK F M,KASNECI G,WEIKUM G.Yago:a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web.2007:697-706. [4]AUER S,BIZER C,KOBILAROV G,et al.Dbpedia:A nucleus for a web of open data[M]//The Semantic Web.Berlin,Heidelberg:Springer,2007:722-735. [5]BORDES A,CHOPRA S,WESTON J.Question answering with subgraph embeddings[J].arXiv:1406.3676,2014. [6]ZHANG F,YUAN N J,LIAN D,et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:353-362. [7]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling relational data with graph convolutional networks[C]//Euro-pean Semantic Web Conference.Cham:Springer,2018:593-607. [8]XIE R,LIU Z,SUN M.Representation Learning of Knowledge Graphs with Hierarchical Types[C]//IJCAI.2016:2965-2971. [9]MA S,DING J,JIA W,et al.Transt:Type-based multiple embedding representations for knowledge graph completion[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Cham:Springer,2017:717-733. [10]HAO J,CHEN M,YU W,et al.Universal representation lear-ning of knowledge bases by jointly embedding instances and ontological concepts[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mi-ning.2019:1709-1719. [11]JAIN P,KUMAR P,CHAKRABARTI S.Type-sensitive know-ledge base inference without explicit typesupervision[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics(Volume 2:Short Papers).2018:75-80. [12]NIU G,LI B,ZHANG Y,et al.AutoETER:Automated entitytype representation for knowledge graph embedding[J].arXiv:2009.12030,2020. [13]DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2d knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018. [14]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[J].Advances in Neural Information Processing Systems,2013,26(2):2787-2795. [15]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2014. [16]SUN Z,DENG Z H,NIE J Y,et al.Rotate:Knowledge graph embedding by relational rotation in complex space[J].arXiv:1902.10197,2019. [17]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//ICML.2011. [18]YANG B,YIH W,HE X,et al.Embedding entities and relations for learning and inferencein knowledge bases[J].arXiv:1412.6575,2014. [19]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.PMLR,2016:2071-2080. [20]SHANG C,TANG Y,HUANG J,et al.End-to-end structure-aware convolutional networks for knowledge base completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:3060-3067. [21]VASHISHTH S,SANYAL S,NITIN V,et al.Composition-based multi-relational graphconvolutional networks[J].arXiv:1911.03082,2019. [22]NATHANI D,CHAUHAN J,SHARMA C,et al.Learning attention-based embeddings for relation prediction in knowledge graphs[J].arXiv:1906.01195,2019. [23]ZHAO X,JIA Y,LI A,et al.Target relational attention-oriented knowledge graph reasoning[J].Neurocomputing,2021,461:577-586. [24]LI R,CAO Y,ZHU Q,et al.How does knowledge graphembed-ding extrapolate to unseen data:a semantic evidence view[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:5781-5791. [25]SUN Z,VASHISHTH S,SANYAL S,et al.A re-evaluation of knowledge graph completion methods[J].arXiv:1911.03903,2019. [26]VASHISHTH S,SANYAL S,NITIN V,et al.Interacte:Improving convolution-based knowledge graph embeddings by increa-sing feature interactions[C]//Proceedings of the AAAI Confe-rence on Artificial Intelligence.2020:3009-3016. |
|
||
首页