English

Graph Representations for Higher-Order Logic and Theorem Proving

Machine Learning 2019-09-16 v2 Artificial Intelligence Logic in Computer Science Machine Learning

Abstract

This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain. Interactive, higher-order theorem provers allow for the formalization of most mathematical theories and have been shown to pose a significant challenge for deep learning. Higher-order logic is highly expressive and, even though it is well-structured with a clearly defined grammar and semantics, there still remains no well-established method to convert formulas into graph-based representations. In this paper, we consider several graphical representations of higher-order logic and evaluate them against the HOList benchmark for higher-order theorem proving.

Keywords

Cite

@article{arxiv.1905.10006,
  title  = {Graph Representations for Higher-Order Logic and Theorem Proving},
  author = {Aditya Paliwal and Sarah Loos and Markus Rabe and Kshitij Bansal and Christian Szegedy},
  journal= {arXiv preprint arXiv:1905.10006},
  year   = {2019}
}
R2 v1 2026-06-23T09:21:24.264Z