Geometric Transformer for End-to-End Molecule Properties Prediction

Yoni Choukroun, Lior Wolf

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Transformers have become methods of choice in many applications thanks to their ability to represent complex interactions between elements. However, extending the Transformer architecture to non-sequential data such as molecules and enabling its training on small datasets remains a challenge. In this work, we introduce a Transformer-based architecture for molecule property prediction, which is able to capture the geometry of the molecule. We modify the classical positional encoder by an initial encoding of the molecule geometry, as well as a learned gated self-attention mechanism. We further suggest an augmentation scheme for molecular data capable of avoiding the overfitting induced by the overparameterized architecture. The proposed framework outperforms the state-of-the-art methods while being based on pure machine learning solely, i.e. the method does not incorporate domain knowledge from quantum chemistry and does not use extended geometric inputs besides the pairwise atomic distances.

Original languageEnglish
Title of host publicationProceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
EditorsLuc De Raedt, Luc De Raedt
PublisherInternational Joint Conferences on Artificial Intelligence
Pages2895-2901
Number of pages7
ISBN (Electronic)9781956792003
StatePublished - 2022
Event31st International Joint Conference on Artificial Intelligence, IJCAI 2022 - Vienna, Austria
Duration: 23 Jul 202229 Jul 2022

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference31st International Joint Conference on Artificial Intelligence, IJCAI 2022
Country/TerritoryAustria
CityVienna
Period23/07/2229/07/22

Fingerprint

Dive into the research topics of 'Geometric Transformer for End-to-End Molecule Properties Prediction'. Together they form a unique fingerprint.

Cite this