COTSAE: CO-Training of Structure and Attribute Embeddings for Entity Alignment

Entity alignment is a fundamental and vital task in Knowledge Graph (KG) construction and fusion. Previous works mainly focus on capturing the structural semantics of entities by learning the entity embeddings on the relational triples and pre-aligned "seed entities". Some works also seek to incorporate the attribute information to assist refining the entity embeddings. However, there are still many problems not considered, which dramatically limits the utilization of attribute information in the entity alignment. Different KGs may have lots of different attribute types, and even the same attribute may have diverse data structures and value granularities. Most importantly, attributes may have various "contributions" to the entity alignment. To solve these problems, we propose COTSAE that combines the structure and attribute information of entities by co-training two embedding learning components, respectively. We also propose a joint attention method in our model to learn the attentions of attribute types and values cooperatively. We verified our COTSAE on several datasets from real-world KGs, and the results showed that it is significantly better than the latest entity alignment methods. The structure and attribute information can complement each other and both contribute to performance improvement.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Gjergji Kasneci,et al.  SIGMa: simple greedy matching for aligning large knowledge bases , 2012, KDD.

[3]  Wei Hu,et al.  Bootstrapping Entity Alignment with Knowledge Graph Embedding , 2018, IJCAI.

[4]  Rui Zhang,et al.  Entity Alignment between Knowledge Graphs Using Attribute Embeddings , 2019, AAAI.

[5]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[6]  Zhiyuan Liu,et al.  Iterative Entity Alignment via Joint Knowledge Embeddings , 2017, IJCAI.

[7]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[8]  Zhen Wang,et al.  Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[9]  Wei Hu,et al.  Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding , 2017, SEMWEB.

[10]  Danqi Chen,et al.  Reasoning With Neural Tensor Networks for Knowledge Base Completion , 2013, NIPS.

[11]  Ke Chen,et al.  Extracting Speaker-Specific Information with a Regularized Siamese Deep Network , 2011, NIPS.

[12]  Steven Skiena,et al.  Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment , 2018, IJCAI.

[13]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[14]  Jun Zhao,et al.  Knowledge Graph Embedding via Dynamic Mapping Matrix , 2015, ACL.

[15]  Carlo Zaniolo,et al.  Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment , 2016, IJCAI.

[16]  Jun Zhao,et al.  A Joint Embedding Method for Entity Alignment of Knowledge Bases , 2016, CCKS.

[17]  Wei Hu,et al.  Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs , 2019, ICML.

[18]  Yuzhong Qu,et al.  Multi-view Knowledge Graph Embedding for Entity Alignment , 2019, IJCAI.

[19]  Yansong Feng,et al.  Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network , 2019, ACL.

[20]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[21]  Zhiyuan Liu,et al.  Learning Entity and Relation Embeddings for Knowledge Graph Completion , 2015, AAAI.

[22]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[23]  Benjamin I. P. Rubinstein,et al.  Principled Graph Matching Algorithms for Integrating Multiple Data Sources , 2014, IEEE Transactions on Knowledge and Data Engineering.

[24]  Pasquale Minervini,et al.  Convolutional 2D Knowledge Graph Embeddings , 2017, AAAI.