Accelerating the inference of string generation-based chemical reaction models for industrial applications

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Andronov, Mikhail, Andronova, Natalia, Wand, Michael, Schmidhuber, Jürgen, Clevert, Djork-Arné
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929423706488832
author Andronov, Mikhail
Andronova, Natalia
Wand, Michael
Schmidhuber, Jürgen
Clevert, Djork-Arné
author_facet Andronov, Mikhail
Andronova, Natalia
Wand, Michael
Schmidhuber, Jürgen
Clevert, Djork-Arné
contents Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis planning systems due to their state-of-the-art accuracy. However, they suffer from slow inference speed. We present a method to accelerate inference in autoregressive SMILES generators through speculative decoding by copying query string subsequences into target strings in the right places. We apply our method to the molecular transformer implemented in Pytorch Lightning and achieve over 3X faster inference in reaction prediction and single-step retrosynthesis, with no loss in accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09685
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accelerating the inference of string generation-based chemical reaction models for industrial applications
Andronov, Mikhail
Andronova, Natalia
Wand, Michael
Schmidhuber, Jürgen
Clevert, Djork-Arné
Machine Learning
Artificial Intelligence
Quantitative Methods
Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis planning systems due to their state-of-the-art accuracy. However, they suffer from slow inference speed. We present a method to accelerate inference in autoregressive SMILES generators through speculative decoding by copying query string subsequences into target strings in the right places. We apply our method to the molecular transformer implemented in Pytorch Lightning and achieve over 3X faster inference in reaction prediction and single-step retrosynthesis, with no loss in accuracy.
title Accelerating the inference of string generation-based chemical reaction models for industrial applications
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2407.09685