English

Premise Selection for Theorem Proving by Deep Graph Embedding

Artificial Intelligence 2017-10-09 v1 Machine Learning Logic in Computer Science

Abstract

We propose a deep learning-based approach to the problem of premise selection: selecting mathematical statements relevant for proving a given conjecture. We represent a higher-order logic formula as a graph that is invariant to variable renaming but still fully preserves syntactic and semantic information. We then embed the graph into a vector via a novel embedding method that preserves the information of edge ordering. Our approach achieves state-of-the-art results on the HolStep dataset, improving the classification accuracy from 83% to 90.3%.

Keywords

Cite

@article{arxiv.1709.09994,
  title  = {Premise Selection for Theorem Proving by Deep Graph Embedding},
  author = {Mingzhe Wang and Yihe Tang and Jian Wang and Jia Deng},
  journal= {arXiv preprint arXiv:1709.09994},
  year   = {2017}
}

Comments

Mingzhe Wang and Yihe Tang contributed equally

R2 v1 2026-06-22T21:57:53.244Z