Aggregating pharmaceutical data in the drug-target interaction (DTI) domain can potentially deliver life-saving breakthroughs. It is, however, notoriously difficult due to regulatory constraints and commercial interests [5, 18]. This work proposes the application of federated learning, which is reconcilable with the industry's constraints. It does not require sharing any information that would reveal the entities' data or any other high-level summary. When used on a representative GraphDTA model and the KIBA dataset, it achieves up to 15% improved performance relative to the best available non-privacy preserving alternative. Our extensive battery of experiments shows that, unlike in other domains, the non-IID data distribution in the DTI datasets does not deteriorate FL performance. Additionally, we identify a material trade-off between the benefits of adding new data and the cost of adding more clients.
A Federated Learning Benchmark for Drug-Target Interaction / Mittone, G.; Svoboda, F.; Aldinucci, M.; Lane, N.; Lio, P.. - (2023), pp. 1177-1181. (Intervento presentato al convegno 2023 World Wide Web Conference, WWW 2023 tenutosi a Austin; usa) [10.1145/3543873.3587687].
A Federated Learning Benchmark for Drug-Target Interaction
Lio P.
2023
Abstract
Aggregating pharmaceutical data in the drug-target interaction (DTI) domain can potentially deliver life-saving breakthroughs. It is, however, notoriously difficult due to regulatory constraints and commercial interests [5, 18]. This work proposes the application of federated learning, which is reconcilable with the industry's constraints. It does not require sharing any information that would reveal the entities' data or any other high-level summary. When used on a representative GraphDTA model and the KIBA dataset, it achieves up to 15% improved performance relative to the best available non-privacy preserving alternative. Our extensive battery of experiments shows that, unlike in other domains, the non-IID data distribution in the DTI datasets does not deteriorate FL performance. Additionally, we identify a material trade-off between the benefits of adding new data and the cost of adding more clients.File | Dimensione | Formato | |
---|---|---|---|
Mottone_A-Federated_2023.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
501.41 kB
Formato
Adobe PDF
|
501.41 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.