Graph Models

NeuroTactic is a model for theorem proving which leverages graph neural networks to represent the theorem and premises, and applies graph contrastive learning for pre-training. Specifically, premise selection is designed as a pretext task for the graph contrastive learning approach. The learned representations are then used for the downstream task, tactic prediction

Source: Graph Contrastive Pre-training for Effective Theorem Reasoning

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Automated Theorem Proving 1 100.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories