Communication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Zihao, Yan, Jia, Zhang, Ying-Jun Angela
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916889689587712
author Hu, Zihao
Yan, Jia
Zhang, Ying-Jun Angela
author_facet Hu, Zihao
Yan, Jia
Zhang, Ying-Jun Angela
contents The ever-growing learning model size nowadays challenges the communication efficiency and privacy preservation of the traditional federated learning (FL). In this paper, we propose a novel differentially private (DP) over-the-air federated distillation (FD) framework, where wireless devices (WDs) periodically share noise-perturbed model outputs with the parameter server by harnessing the superposition property of multi-access channels. Accordingly, over-the-air FD enables the shared responsibility of the DP preservation on the low-dimensional disclosed signals among WDs. We study the communication-learning co-design problem in differentially private over-the-air FD, aiming to maximize the learning convergence rate while meeting the transmit power and DP requirements of WDs. The main challenge is rooted in the intractable learning and privacy analysis in over-the-air FD, together with the strong coupling among the decision variables spanning two timescales. To tackle this problem, we first derive the analytical learning convergence rate and privacy losses of WDs, based on which the optimal transceiver design per FD round and long-term training rounds decision are obtained in the closed forms. Numerical results demonstrate that the proposed differentially private over-the-air FD approach achieves a better learning-privacy trade-off with largely-reduced communication overhead than the conventional FL benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06557
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Communication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillation
Hu, Zihao
Yan, Jia
Zhang, Ying-Jun Angela
Information Theory
Machine Learning
Signal Processing
The ever-growing learning model size nowadays challenges the communication efficiency and privacy preservation of the traditional federated learning (FL). In this paper, we propose a novel differentially private (DP) over-the-air federated distillation (FD) framework, where wireless devices (WDs) periodically share noise-perturbed model outputs with the parameter server by harnessing the superposition property of multi-access channels. Accordingly, over-the-air FD enables the shared responsibility of the DP preservation on the low-dimensional disclosed signals among WDs. We study the communication-learning co-design problem in differentially private over-the-air FD, aiming to maximize the learning convergence rate while meeting the transmit power and DP requirements of WDs. The main challenge is rooted in the intractable learning and privacy analysis in over-the-air FD, together with the strong coupling among the decision variables spanning two timescales. To tackle this problem, we first derive the analytical learning convergence rate and privacy losses of WDs, based on which the optimal transceiver design per FD round and long-term training rounds decision are obtained in the closed forms. Numerical results demonstrate that the proposed differentially private over-the-air FD approach achieves a better learning-privacy trade-off with largely-reduced communication overhead than the conventional FL benchmarks.
title Communication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillation
topic Information Theory
Machine Learning
Signal Processing
url https://arxiv.org/abs/2508.06557