Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-Based SVM - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2021

Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-Based SVM

Résumé

A crucial step to assure drug safety is predicting off-target binding. For oligonucleotide drugs this requires learning the relevant thermodynamics from often large-scale data distributed across different organisations. This process will respect data privacy if distributed and private learning under limited and private communication between local nodes is used. We propose an ADMM-based SVM with differential privacy for this purpose. We empirically show that this approach achieves accuracy comparable to the non-private one, i.e. ∼86%, while yielding tight empirical privacy guarantees even after convergence.
Fichier non déposé

Dates et versions

hal-03841224 , version 1 (07-11-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Shirin Tavara, Alexander Schliep, Debabrota Basu. Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-Based SVM. Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 1525, Springer International Publishing; Springer International Publishing, pp.459-467, 2021, Communications in Computer and Information Science, ⟨10.1007/978-3-030-93733-1_34⟩. ⟨hal-03841224⟩
43 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More