In Machine Learning, the data for training the model are stored centrally. However, when the data come from different sources and contain sensitive information, we can use federated learning to implement a privacy-preserving distributed machine learning framework. In this case, multiple client devices participate in global model training by sharing only the model updates with the server while keeping the original data local. In this paper, we propose a new approach, called partially-federated learning, that combines machine learning with federated learning. This hybrid architecture can train a unified model across multiple clients, where the individual client can decide whether a sample must remain private or can be shared with the server. This decision is made by a privacy module that can enforce various techniques to protect the privacy of client data. The proposed approach improves the performance compared to classical federated learning.
Partially-federated learning: A new approach to achieving privacy and effectiveness / Fisichella, Marco; Lax, Gianluca; Russo, Antonia. - In: INFORMATION SCIENCES. - ISSN 0020-0255. - 614:(2022), pp. 534-547. [10.1016/j.ins.2022.10.082]
Partially-federated learning: A new approach to achieving privacy and effectiveness
Lax Gianluca
;Russo Antonia
2022-01-01
Abstract
In Machine Learning, the data for training the model are stored centrally. However, when the data come from different sources and contain sensitive information, we can use federated learning to implement a privacy-preserving distributed machine learning framework. In this case, multiple client devices participate in global model training by sharing only the model updates with the server while keeping the original data local. In this paper, we propose a new approach, called partially-federated learning, that combines machine learning with federated learning. This hybrid architecture can train a unified model across multiple clients, where the individual client can decide whether a sample must remain private or can be shared with the server. This decision is made by a privacy module that can enforce various techniques to protect the privacy of client data. The proposed approach improves the performance compared to classical federated learning.File | Dimensione | Formato | |
---|---|---|---|
Fisichella_2022_j.ins_partially_editor.pdf
non disponibili
Descrizione: Versione editoriale
Tipologia:
Versione Editoriale (PDF)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.47 MB
Formato
Adobe PDF
|
1.47 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Fisichella_2022_j.ins_partially_post.pdf
embargo fino al 20/10/2024
Descrizione: Post-print
Tipologia:
Documento in Post-print
Licenza:
Creative commons
Dimensione
1.23 MB
Formato
Adobe PDF
|
1.23 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.