Can Graph Neural Networks Help Logic Reasoning?
This work addresses a long-standing problem in machine learning for researchers and practitioners, offering a scalable solution to computationally intensive probabilistic logic inference, though it appears incremental as it builds on existing methods.
The paper tackles the challenge of combining logic reasoning and probabilistic inference efficiently, proposing ExpressGNN, a variant of graph neural networks, which scales to large datasets and shows potential for advancing probabilistic logic reasoning.
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.