Reinforcement Learning for Scalable Logic Optimization with Graph Neural Networks

Xavier Timoneda; Lukas Cavigelli

Reinforcement Learning for Scalable Logic Optimization with Graph Neural Networks

Machine Learning 2021-05-06 v1

Authors: Xavier Timoneda , Lukas Cavigelli

Abstract

Logic optimization is an NP-hard problem commonly approached through hand-engineered heuristics. We propose to combine graph convolutional networks with reinforcement learning and a novel, scalable node embedding method to learn which local transforms should be applied to the logic graph. We show that this method achieves a similar size reduction as ABC on smaller circuits and outperforms it by 1.5-1.75x on larger random graphs.

Keywords

graph representation learning neural network graph neural network

Cite

@article{arxiv.2105.01755,
  title  = {Reinforcement Learning for Scalable Logic Optimization with Graph Neural Networks},
  author = {Xavier Timoneda and Lukas Cavigelli},
  journal= {arXiv preprint arXiv:2105.01755},
  year   = {2021}
}

Related papers

View all related →