Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments show that iteratively learning embeddings and rules benefit each other during learning and prediction.

[1]  Evgeny Kharlamov,et al.  Rule Learning from Knowledge Graphs Guided by Embedding Models , 2018, SEMWEB.

[2]  Yiming Yang,et al.  Analogical Inference for Multi-relational Embeddings , 2017, ICML.

[3]  Li Guo,et al.  Jointly Embedding Knowledge Graphs and Logical Rules , 2016, EMNLP.

[4]  Nicholas Jing Yuan,et al.  Collaborative Knowledge Base Embedding for Recommender Systems , 2016, KDD.

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

[6]  Zhen Wang,et al.  Knowledge Graph and Text Jointly Embedding , 2014, EMNLP.

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

[8]  Evgeniy Gabrilovich,et al.  A Review of Relational Machine Learning for Knowledge Graphs , 2015, Proceedings of the IEEE.

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

[10]  Thomas Demeester,et al.  Lifted Rule Injection for Relation Embeddings , 2016, EMNLP.

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

[12]  Kewen Wang,et al.  Scalable Rule Learning via Learning Representation , 2018, IJCAI.

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

[14]  Fan Yang,et al.  Differentiable Learning of Logical Rules for Knowledge Base Reasoning , 2017, NIPS.

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

[16]  Steven Schockaert,et al.  From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules , 2018, KR.

[17]  Minlie Huang,et al.  SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions , 2016, AAAI.

[18]  Fabian M. Suchanek,et al.  AMIE: association rule mining under incomplete evidence in ontological knowledge bases , 2013, WWW.

[19]  Yelong Shen,et al.  Modeling Large-Scale Structured Relationships with Shared Memory for Knowledge Base Completion , 2016, Rep4NLP@ACL.

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

[21]  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.

[22]  Antoine Bordes,et al.  Composing Relationships with Translations , 2015, EMNLP.

[23]  Juan-Zi Li,et al.  Text-Enhanced Representation Learning for Knowledge Graph , 2016, IJCAI.

[24]  Li Guo,et al.  Semantically Smooth Knowledge Graph Embedding , 2015, ACL.

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

[26]  Seung-won Hwang,et al.  KBQA: Learning Question Answering over QA Corpora and Knowledge Bases , 2019, Proc. VLDB Endow..

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

[28]  Li Guo,et al.  Knowledge Base Completion Using Embeddings and Rules , 2015, IJCAI.

[29]  Qing Liu,et al.  SWARM: An Approach for Mining Semantic Association Rules from Semantic Web Data , 2016, PRICAI.

[30]  Vít Novácek,et al.  Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms , 2017, ECML/PKDD.

[31]  Wei Zhang,et al.  Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding , 2018, EMNLP.

[32]  Wen Zhang,et al.  Knowledge Graph Embedding with Diversity of Structures , 2017, WWW.

[33]  Li Guo,et al.  Improving Knowledge Graph Embedding Using Simple Constraints , 2018, ACL.

[34]  Huanbo Luan,et al.  Image-embodied Knowledge Representation Learning , 2016, IJCAI.

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

[36]  Fabian M. Suchanek,et al.  Fast rule mining in ontological knowledge bases with AMIE+\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$+$$\end{docu , 2015, The VLDB Journal.

[37]  Zhiyuan Liu,et al.  Representation Learning of Knowledge Graphs with Hierarchical Types , 2016, IJCAI.

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

[39]  Li Guo,et al.  Knowledge Graph Embedding with Iterative Guidance from Soft Rules , 2017, AAAI.

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

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

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

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

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

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

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

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

[48]  Petr Hájek,et al.  Metamathematics of Fuzzy Logic , 1998, Trends in Logic.

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

[50]  Juan-Zi Li,et al.  RDF2Rules: Learning Rules from RDF Knowledge Bases by Mining Frequent Predicate Cycles , 2015, ArXiv.