Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs

Abstract

Knowledge graph reasoning is the fundamental component to support machine learning applications such as information extraction, information retrieval, and recommendation. Since knowledge graphs can be viewed as the discrete symbolic representations of knowledge, reasoning on knowledge graphs can naturally leverage the symbolic techniques. However, symbolic reasoning is intolerant of the ambiguous and noisy data. On the contrary, the recent advances of deep learning promote neural reasoning on knowledge graphs, which is robust to the ambiguous and noisy data, but lacks interpretability compared to symbolic reasoning. Considering the advantages and disadvantages of both methodologies, recent efforts have been made on combining the two reasoning methods. In this survey, we take a thorough look at the development of the symbolic, neural and hybrid reasoning on knowledge graphs. We survey two specific reasoning tasks, knowledge graph completion and question answering on knowledge graphs, and explain them in a unified reasoning framework. We also briefly discuss the future directions for knowledge graph reasoning.

arXiv comment29 pages, AI Open Journal 2021

References in corpus (31)

• Auto-Encoding Variational Bayes
• Semi-Supervised Classification with Graph Convolutional Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• Language Models are Few-Shot Learners
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
• Variational Reasoning for Question Answering with Knowledge Graph
• Lambda Dependency-Based Compositional Semantics
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
• Probabilistic Logic Neural Networks for Reasoning
• An Interpretable Reasoning Network for Multi-Relation Question Answering
• Character-Level Question Answering with Attention
• TransG : A Generative Mixture Model for Knowledge Graph Embedding
• Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
• TensorLog: A Differentiable Deductive Database
• Relation Embedding with Dihedral Group in Knowledge Graph
• Inductive Relation Prediction by Subgraph Reasoning
• Embedding Logical Queries on Knowledge Graphs
• A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
• Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion
• Graph Neural Networks with Generated Parameters for Relation Extraction
• Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
• Faithful Embeddings for Knowledge Base Queries
• Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval
• Logic Rules Powered Knowledge Graph Embedding
• Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
• Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference