Graph Reasoning Networks

Markus Zopf; Francesco Alesiani

Graph Reasoning Networks

Machine Learning 2024-07-09 v1 Artificial Intelligence

Authors: Markus Zopf , Francesco Alesiani

Abstract

Graph neural networks (GNNs) are the predominant approach for graph-based machine learning. While neural networks have shown great performance at learning useful representations, they are often criticized for their limited high-level reasoning abilities. In this work, we present Graph Reasoning Networks (GRNs), a novel approach to combine the strengths of fixed and learned graph representations and a reasoning module based on a differentiable satisfiability solver. While results on real-world datasets show comparable performance to GNN, experiments on synthetic datasets demonstrate the potential of the newly proposed method.

Keywords

graph neural network graph generation graph representation learning

Cite

@article{arxiv.2407.05816,
  title  = {Graph Reasoning Networks},
  author = {Markus Zopf and Francesco Alesiani},
  journal= {arXiv preprint arXiv:2407.05816},
  year   = {2024}
}

Comments

Presented at the workshop on graphs and more complex structures for learning and reasoning at AAAI 2022

Related papers

View all related →