Reaction prediction is a fundamental problem in computational chemistry. Existing approaches typically generate a chemical reaction by sampling tokens or graph edits sequentially, conditioning on previously generated outputs. These autoregressive generating methods impose an arbitrary ordering of outputs and prevent parallel decoding during inference. We devise a novel decoder that avoids such sequential generating and predicts the reaction in a Non-Autoregressive manner. Inspired by physical-chemistry insights, we represent edge edits in a molecule graph as electron flows, which can then be predicted in parallel. To capture the uncertainty of reactions, we introduce latent variables to generate multi-modal outputs. Following previous works, we evaluate our model on USPTO MIT dataset. Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.
@article{arxiv.2012.12124,
title = {Non-autoregressive electron flow generation for reaction prediction},
author = {Hangrui Bi and Hengyi Wang and Chence Shi and Jian Tang},
journal= {arXiv preprint arXiv:2012.12124},
year = {2021}
}
Comments
We find that some sections of the paper is not well writen and may confuse the readers. We are working on rewriting these parts and would like to withdraw the preprint before resubmitting or replacement