Efficient Probabilistic Logic Reasoning with Graph Neural Networks

Abstract

Markov Logic Networks (MLNs), which elegantly combine logic rules and probabilistic graphical models, can be used to address many knowledge graph problems. However, inference in MLN is computationally intensive, making the industrial-scale application of MLN very difficult. In recent years, graph neural networks (GNNs) have emerged as efficient and effective tools for large-scale graph problems. Nevertheless, GNNs do not explicitly incorporate prior logic rules into the models, and may require many labeled examples for a target task. In this paper, we explore the combination of MLNs and GNNs, and use graph neural networks for variational inference in MLN. We propose a GNN variant, named ExpressGNN, which strikes a nice balance between the representation power and the simplicity of the model. Our extensive experiments on several benchmark datasets demonstrate that ExpressGNN leads to effective and efficient probabilistic logic reasoning.

References in corpus (3)

• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Discriminative Embeddings of Latent Variable Models for Structured Data
• GMNN: Graph Markov Neural Networks

Cited by in corpus (14)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Graph Neural Networks: Taxonomy, Advances and Trends
• Neural Collaborative Reasoning
• RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
• Generalization and Representational Limits of Graph Neural Networks
• A Survey on Graph Neural Networks for Knowledge Graph Completion
• Deep Graph Neural Networks with Shallow Subgraph Samplers
• Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results
• A Survey on Neural-symbolic Learning Systems
• Topological Regularization for Graph Neural Networks Augmentation
• Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting
• On the Importance of Sampling in Training GCNs: Tighter Analysis and Variance Reduction
• Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective
• Learning Logic Rules for Document-level Relation Extraction