# Can Graph Neural Networks Help Logic Reasoning?

arXiv: https://arxiv.org/abs/1906.02111 · HTML: https://mlsanity.com/paper/1906.02111/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 5 of 5)

- [Network representation learning: A macro and micro view](https://mlsanity.com/paper/2111.10772/) (2021)
- [Enhancing Embedding Representations of Biomedical Data using Logic Knowledge](https://mlsanity.com/paper/2303.13566/) (2023)
- [Knowledgebra: An Algebraic Learning Framework for Knowledge Graph](https://mlsanity.com/paper/2204.07328/) (2022)
- [Simple Rule Injection for ComplEx Embeddings](https://mlsanity.com/paper/2308.03269/) (2023)
- [ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction](https://mlsanity.com/paper/2511.23340/) (2025)

## Abstract (arXiv)

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.