Poster
Premise Selection for Theorem Proving by Deep Graph Embedding
Mingzhe Wang · Yihe Tang · Jian Wang · Jia Deng
Pacific Ballroom #92
Keywords: [ Deep Learning ] [ Embedding Approaches ] [ Applications ]
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%.
Live content is unavailable. Log in and register to view live content