NeuroTactic

2000년 도입 · 논문 1편에서 사용

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

출처: Graph Contrastive Pre-training for Effective Theorem Reasoning

소개 논문: Graph Contrastive Pre-training for Effective Theorem Reasoning