A Bi-directional Relation Aware Network for Link Prediction in Knowledge Graph

Knowledge graph embedding technique aims to represent elements in knowledge graph, such as entities and relations, with numerical embedding vectors in semantic spaces. In general, an existing knowledge graph has relatively stable number of entities and directional relations before being updated. Though existing research has utilized relations of entities for link predication in knowledge graph, the relational directivity feature has not been fully exploited. Therefore, this paper proposes a bi-directional relation aware network (BDRAN) for representation learning, mining information based on directivity of relations in existing knowledge graphs. BDRAN leverages an encoder to capture features of entities in different patterns with diverse directional relations in entity representation level and semantic representation level. Besides, decoder is used to simulate interactions between entities and relations for precise representation learning. Experiments are conducted with widely used standard datasets including WN18RR, FB15k-237, NELL-995 and Kinship. The results present the improvement of BDRAN on the datasets, demonstrating the effectiveness of our model for link prediction.

[1]  Hai Liu,et al.  Aggregating neighborhood information for negative sampling for knowledge graph embedding , 2020, Neural Computing and Applications.

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

[3]  Yaohui Jin,et al.  TransMS: Knowledge Graph Embedding for Complex Relations by Multidirectional Semantics , 2019, IJCAI.

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

[5]  Zhendong Mao,et al.  Knowledge Graph Embedding: A Survey of Approaches and Applications , 2017, IEEE Transactions on Knowledge and Data Engineering.

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

[7]  Estevam R. Hruschka,et al.  Toward an Architecture for Never-Ending Language Learning , 2010, AAAI.

[8]  Zihan Wang,et al.  Robust Embedding with Multi-Level Structures for Link Prediction , 2019, IJCAI.

[9]  Tianyong Hao,et al.  A Knowledge Selective Adversarial Network for Link Prediction in Knowledge Graph , 2019, NLPCC.

[10]  Hans-Peter Kriegel,et al.  A Three-Way Model for Collective Learning on Multi-Relational Data , 2011, ICML.

[11]  Guillaume Bouchard,et al.  Complex Embeddings for Simple Link Prediction , 2016, ICML.

[12]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[14]  William Yang Wang,et al.  KBGAN: Adversarial Learning for Knowledge Graph Embeddings , 2017, NAACL.

[15]  Michael Gamon,et al.  Representing Text for Joint Embedding of Text and Knowledge Bases , 2015, EMNLP.

[16]  Jianfeng Gao,et al.  Embedding Entities and Relations for Learning and Inference in Knowledge Bases , 2014, ICLR.

[17]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[18]  Seyed Mehran Kazemi,et al.  SimplE Embedding for Link Prediction in Knowledge Graphs , 2018, NeurIPS.