MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning

Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships. We extend existing works to consider a generalized form of multi-hop rules, where each rule is a set of relation chains. To learn such generalized rules efficiently, we propose a two-step approach that first selects a small set of relation chains as a rule and then evaluates the confidence of the target relationship by jointly scoring the selected chains. A game-theoretical framework is proposed to this end to simultaneously optimize the rule selection and prediction steps. Empirical results show that our multi-chain multi-hop (MCMH) rules result in superior results compared to the standard single-chain approaches, justifying both our formulation of generalized rules and the effectiveness of the proposed learning framework.

[1]  Alexander J. Smola,et al.  Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning , 2017, ICLR.

[2]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[3]  Zhiyuan Liu,et al.  Representation Learning of Knowledge Graphs with Entity Descriptions , 2016, AAAI.

[4]  Tom M. Mitchell,et al.  Random Walk Inference and Learning in A Large Scale Knowledge Base , 2011, EMNLP.

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

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

[7]  Ni Lao,et al.  Relational retrieval using a combination of path-constrained random walks , 2010, Machine Learning.

[8]  Yuanzhuo Wang,et al.  Knowledge Graph Embedding , 2017, ACM Trans. Web.

[9]  Tim Weninger,et al.  ProjE: Embedding Projection for Knowledge Graph Completion , 2016, AAAI.

[10]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[11]  M. Gates,et al.  Non-Parametric Reasoning on Knowledge Bases , 2020 .

[12]  Tommi S. Jaakkola,et al.  Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control , 2019, EMNLP.

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

[14]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

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

[16]  Yi Zhang,et al.  Average Precision , 2009, Encyclopedia of Database Systems.

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

[18]  Wenhu Chen,et al.  Variational Knowledge Graph Reasoning , 2018, NAACL.

[19]  Regina Barzilay,et al.  Rationalizing Neural Predictions , 2016, EMNLP.

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

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

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

[23]  Le Song,et al.  Variational Reasoning for Question Answering with Knowledge Graph , 2017, AAAI.

[24]  Qiaozhu Mei,et al.  Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts , 2018, EMNLP.

[25]  Ralph Grishman,et al.  Distant Supervision for Relation Extraction with an Incomplete Knowledge Base , 2013, NAACL.

[26]  Yelong Shen,et al.  ReinforceWalk: Learning to Walk in Graph with Monte Carlo Tree Search , 2018, ICLR.

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

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

[29]  Richard Socher,et al.  Multi-Hop Knowledge Graph Reasoning with Reward Shaping , 2018, EMNLP.

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

[31]  Wenhan Xiong,et al.  DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning , 2017, EMNLP.

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

[33]  Andrew McCallum,et al.  Compositional Vector Space Models for Knowledge Base Completion , 2015, ACL.