Non-autoregressive electron flow generation for reaction prediction

TL;DR

This paper introduces a non-autoregressive method for reaction prediction in computational chemistry, predicting electron flows in parallel to improve speed without sacrificing accuracy.

Contribution

It proposes a novel decoder that predicts reaction outcomes in parallel using electron flows, reducing inference latency and capturing reaction uncertainty with latent variables.

Findings

Achieves an order of magnitude lower inference latency.

Attains state-of-the-art top-1 accuracy.

Performs comparably on Top-K sampling.

Abstract

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.