Can Graph Neural Networks Help Logic Reasoning?

Abstract

Effectively combining logic reasoning and probabilistic inference has been a long-standing goal of machine learning: the former has the ability to generalize with small training data, while the latter provides a principled framework for dealing with noisy data. However, existing methods for combining the best of both worlds are typically computationally intensive. In this paper, we focus on Markov Logic Networks and explore the use of graph neural networks (GNNs) for representing probabilistic logic inference. It is revealed from our analysis that the representation power of GNN alone is not enough for such a task. We instead propose a more expressive variant, called ExpressGNN, which can perform effective probabilistic logic inference while being able to scale to a large number of entities. We demonstrate by several benchmark datasets that ExpressGNN has the potential to advance probabilistic logic reasoning to the next stage.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Inductive Representation Learning on Large Graphs
• Discriminative Embeddings of Latent Variable Models for Structured Data
• How Powerful are Graph Neural Networks?
• Graph Isomorphism in Quasipolynomial Time
• GMNN: Graph Markov Neural Networks
• Hinge-Loss Markov Random Fields and Probabilistic Soft Logic

Cited by in corpus (3)

• Probabilistic Logic Neural Networks for Reasoning
• Group Representation Theory for Knowledge Graph Embedding
• Network representation learning: A macro and micro view