Search Results for author:
Found 5 papers, 3 papers with code
Graph2Tac: Learning Hierarchical Representations of Math Concepts in Theorem proving
G2T is an online model that is deeply integrated into the users' workflow and can adapt in real time to new Coq projects and their definitions.
Graph Neural Networks For Mapping Variables Between Programs -- Extended Version
Typically, in order to compare two programs, a relation between both programs' sets of variables is required.
Machine Learning Meets The Herbrand Universe
In particular, we develop a GNN2RNN architecture based on an invariant graph neural network (GNN) that learns from problems and their solutions independently of symbol names (addressing the abundance of skolems), combined with a recurrent neural network (RNN) that proposes for each clause its instantiations.
The Isabelle ENIGMA
We significantly improve the performance of the E automated theorem prover on the Isabelle Sledgehammer problems by combining learning and theorem proving in several ways.
Learning Equational Theorem Proving
On these tasks, 3SIL is shown to significantly outperform several established RL and imitation learning methods.
