Details
| Original language | English |
|---|---|
| Pages (from-to) | 534-547 |
| Number of pages | 14 |
| Journal | Information sciences |
| Volume | 614 |
| Early online date | 20 Oct 2022 |
| Publication status | Published - Oct 2022 |
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.
Keywords
- Collaborative learning, Distributed databases, k-anonymity, l-diversity, Machine learning
ASJC Scopus subject areas
- Mathematics(all)
- Theoretical Computer Science
- Computer Science(all)
- Software
- Engineering(all)
- Control and Systems Engineering
- Computer Science(all)
- Computer Science Applications
- Decision Sciences(all)
- Information Systems and Management
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Information sciences, Vol. 614, 10.2022, p. 534-547.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Partially-federated learning
T2 - A new approach to achieving privacy and effectiveness
AU - Fisichella, Marco
AU - Lax, Gianluca
AU - Russo, Antonia
PY - 2022/10
Y1 - 2022/10
N2 - 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.
AB - 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.
KW - Collaborative learning
KW - Distributed databases
KW - k-anonymity
KW - l-diversity
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85140979213&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2022.10.082
DO - 10.1016/j.ins.2022.10.082
M3 - Article
AN - SCOPUS:85140979213
VL - 614
SP - 534
EP - 547
JO - Information sciences
JF - Information sciences
SN - 0020-0255
ER -