Please use this identifier to cite or link to this item:
Title: Differentially-Private Distributed Machine Learning with Partial Worker Attendance: A Flexible and Efficient Approach
Authors: Le, Trieu Phong
Tran, Thi Phuong
Keywords: Differential privacy
Partial attendance
Communication efficiency
Distributed machine learning
Issue Date: Jul-2023
Publisher: Springer Nature
Abstract: In distributed machine learning, multiple machines or workers collaborate to train a model. However, prior research in cross-silo distributed learning with differential privacy has the drawback of requiring all workers to participate in each training iteration, hindering flexibility and efficiency. To overcome these limitations, we introduce a new algorithm that allows partial worker attendance in the training process, reducing communication costs by over 50% while preserving accuracy on benchmark data. The privacy of the workers is also improved because less data are exchanged between workers.
Description: Lecture Notes in Networks and Systems (LNNS, volume 734); CITA: Conference on Information Technology and its Applications; pp: 15-24.
ISBN: 978-3-031-36886-8
Appears in Collections:CITA 2023 (International)

Files in This Item:

 Sign in to read

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.