PuSH - Publikationsserver des Helmholtz Zentrums München

Karpov, P. ; Godin, G.* ; Tetko, I.V.

A transformer model for retrosynthesis.

Lect. Notes Comput. Sc. 11731 LNCS, 817-830 (2019)
Verlagsversion DOI
Open Access Gold (Paid Option)
Creative Commons Lizenzvertrag
We describe a Transformer model for a retrosynthetic reaction prediction task. The model is trained on 45 033 experimental reaction examples extracted from USA patents. It can successfully predict the reactants set for 42.7% of cases on the external test set. During the training procedure, we applied different learning rate schedules and snapshot learning. These techniques can prevent overfitting and thus can be a reason to get rid of internal validation dataset that is advantageous for deep models with millions of parameters. We thoroughly investigated different approaches to train Transformer models and found that snapshot learning with averaging weights on learning rates minima works best. While decoding the model output probabilities there is a strong influence of the temperature that improves at $$\text {T}=1.3$$ the accuracy of models up to 1–2%.
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Character-based Models ; Computer Aided Synthesis Planning ; Retrosynthesis Prediction ; Transformer
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Quellenangaben Band: 11731 LNCS, Heft: , Seiten: 817-830 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]