Learning Theorem Proving Components
This work addresses a bottleneck in automated theorem proving for researchers and practitioners, but it is incremental as it builds on prior GNN-based methods.
The paper tackled the problem of clause selection in automated theorem provers by advancing contextual evaluation using graph neural networks, resulting in improved performance of the E/ENIGMA system.
Saturation-style automated theorem provers (ATPs) based on the given clause procedure are today the strongest general reasoners for classical first-order logic. The clause selection heuristics in such systems are, however, often evaluating clauses in isolation, ignoring other clauses. This has changed recently by equipping the E/ENIGMA system with a graph neural network (GNN) that chooses the next given clause based on its evaluation in the context of previously selected clauses. In this work, we describe several algorithms and experiments with ENIGMA, advancing the idea of contextual evaluation based on learning important components of the graph of clauses.