Startseite
English
Erweiterte Suche
Durchblättern nach ...
Publikationen im Überblick
Ansprechpartner
Hilfe
Postprint
 |
|
möglich sobald bei der ZB eingereicht worden ist.
Synergistic benefits of joint molecule generation and property prediction.
Trans. Machine Learn. Res. 2026-January, 1-32 (2026)
Modeling the joint distribution of data samples and their properties allows to construct a single model for both data generation and property prediction, with synergistic benefits reaching beyond purely generative or predictive models. However, training joint models presents daunting architectural and optimization challenges. Here, we propose Hyformer, a transformer-based joint model that successfully blends the generative and predictive functionalities, using an alternating attention mechanism and a joint pre-training scheme. We show that Hyformer is simultaneously optimized for molecule generation and property prediction, while exhibiting synergistic benefits in conditional sampling, out-of-distribution property prediction and representation learning. Finally, we demonstrate the benefits of joint learning in a drug design use case of discovering novel antimicrobial peptides.
Weitere Metriken?
Zusatzinfos bearbeiten
[➜Einloggen]
Publikationstyp
Artikel: Journalartikel
Dokumenttyp
Wissenschaftlicher Artikel
ISSN (print) / ISBN
2835-8856
e-ISSN
2835-8856
Zeitschrift
Transactions on Machine Learning Research
Quellenangaben
Band: 2026-January,
Seiten: 1-32
Verlag
Journal of Machine Learning Research Inc.
Begutachtungsstatus
Peer reviewed
Institut(e)
Institute of AI for Health (AIH)