Directed Graph Networks for Logical Entailment

EasyChair Preprint 2185, version 3

Abstract

We introduce a neural model for approximate logical reasoning based upon learned bi-directional graph convolutions on directed syntax graphs. The model avoids inflexible inductive bias found in some previous work on this domain, while still producing competitive results on a benchmark propositional entailment dataset. We further demonstrate the generality of our work in a first-order context with a premise selection task. Such models have applications for learned functions of logical data, such as in guiding theorem provers.

Keyphrases: Graph Neural Network, Logical Entailment, automated reasoning, directed acyclic graph

@booklet{EasyChair:2185,
  author    = {Michael Rawson and Giles Reger},
  title     = {Directed Graph Networks for Logical Entailment},
  howpublished = {EasyChair Preprint 2185},
  year      = {EasyChair, 2020}}