Multi-view Classification Model for Knowledge Graph Completion

Most previous work on knowledge graph completion conducted single-view prediction or calculation for candidate triple evaluation, based only on the content information of the candidate triples. This paper describes a novel multi-view classification model for knowledge graph completion, where multiple classification views are performed based on both content and context information for candidate triple evaluation. Each classification view evaluates the validity of a candidate triple from a specific viewpoint, based on the content information inside the candidate triple and the context information nearby the triple. These classification views are implemented by a unified neural network and the classification predictions are weightedly integrated to obtain the final evaluation. Experiments show that, the multi-view model brings very significant improvements over previous methods, and achieves the new state-of-the-art on two representative datasets. We believe that, the flexibility and the scalability of the multi-view classification model facilitates the introduction of additional information and resources for better performance.

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

[2]  Heiko Paulheim,et al.  Global RDF Vector Space Embeddings , 2017, SEMWEB.

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

[4]  Gerhard Weikum,et al.  NAGA: Searching and Ranking Knowledge , 2008, 2008 IEEE 24th International Conference on Data Engineering.

[5]  Jian Tang,et al.  Probabilistic Logic Neural Networks for Reasoning , 2019, NeurIPS.

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

[7]  Jian-Yun Nie,et al.  RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space , 2018, ICLR.

[8]  Rajarshi Das,et al.  Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks , 2016, EACL.

[9]  Timothy M. Hospedales,et al.  TuckER: Tensor Factorization for Knowledge Graph Completion , 2019, EMNLP.

[10]  Bin Wang,et al.  Adaptive Convolution for Multi-Relational Learning , 2019, NAACL.

[11]  Heiko Paulheim,et al.  RDF2Vec: RDF Graph Embeddings for Data Mining , 2016, SEMWEB.

[12]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[13]  Rahul Gupta,et al.  Knowledge base completion via search-based question answering , 2014, WWW.

[14]  Simone Paolo Ponzetto,et al.  Knowledge-based graph document modeling , 2014, WSDM.

[15]  Lorenzo Rosasco,et al.  Holographic Embeddings of Knowledge Graphs , 2015, AAAI.

[16]  Danqi Chen,et al.  Observed versus latent features for knowledge base and text inference , 2015, CVSC.

[17]  Mathias Niepert,et al.  KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features , 2017, UAI.

[18]  Jens Lehmann,et al.  DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia , 2015, Semantic Web.

[19]  Tom M. Mitchell,et al.  Leveraging Knowledge Bases in LSTMs for Improving Machine Reading , 2017, ACL.

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

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

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

[23]  James P. Callan,et al.  Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding , 2017, WWW.

[24]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[25]  Huanbo Luan,et al.  Modeling Relation Paths for Representation Learning of Knowledge Bases , 2015, EMNLP.

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

[27]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

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

[29]  Lizhen Qu,et al.  STransE: a novel embedding model of entities and relationships in knowledge bases , 2016, NAACL.

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

[31]  Hua Wu,et al.  An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge , 2017, ACL.

[32]  Dat Quoc Nguyen.  An overview of embedding models of entities and relationships for knowledge base completion , 2017, ArXiv.

[33]  Hua Wu,et al.  Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information , 2016, ArXiv.

[34]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[35]  Minlie Huang,et al.  GAKE: Graph Aware Knowledge Embedding , 2016, COLING.

[36]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.