Probabilistic Logic Neural Networks for Reasoning

Abstract

Knowledge graph reasoning, which aims at predicting the missing facts through reasoning with the observed facts, is critical to many applications. Such a problem has been widely explored by traditional logic rule-based approaches and recent knowledge graph embedding methods. A principled logic rule-based approach is the Markov Logic Network (MLN), which is able to leverage domain knowledge with first-order logic and meanwhile handle their uncertainty. However, the inference of MLNs is usually very difficult due to the complicated graph structures. Different from MLNs, knowledge graph embedding methods (e.g. TransE, DistMult) learn effective entity and relation embeddings for reasoning, which are much more effective and efficient. However, they are unable to leverage domain knowledge. In this paper, we propose the probabilistic Logic Neural Network (pLogicNet), which combines the advantages of both methods. A pLogicNet defines the joint distribution of all possible triplets by using a Markov logic network with first-order logic, which can be efficiently optimized with the variational EM algorithm. In the E-step, a knowledge graph embedding model is used for inferring the missing triplets, while in the M-step, the weights of logic rules are updated based on both the observed and predicted triplets. Experiments on multiple knowledge graphs prove the effectiveness of pLogicNet over many competitive baselines.

arXiv commentNeurIPS 2019

References in corpus (10)

• Auto-Encoding Variational Bayes
• A Review of Relational Machine Learning for Knowledge Graphs
• Loopy Belief Propagation for Approximate Inference: An Empirical Study
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• GMNN: Graph Markov Neural Networks
• CLP(BN): Constraint Logic Programming for Probabilistic Knowledge
• M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
• Automatic Synonym Discovery with Knowledge Bases
• Can Graph Neural Networks Help Logic Reasoning?

Cited by in corpus (14)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Logic Tensor Networks
• Knowledge Graph Reasoning with Relational Digraph
• Neural Collaborative Reasoning
• RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
• CoKE: Contextualized Knowledge Graph Embedding
• LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
• PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
• A Survey on Neural-symbolic Learning Systems
• Group Representation Theory for Knowledge Graph Embedding
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs
• EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective
• Learning Logic Rules for Document-level Relation Extraction