Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

By Anis Elgabli, Jihong Park, Chaouki Ben Issaid, Medhi Bennis. 2020

72 citations recorded by the source corpus.

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker’s model update while multiple workers’ updates incur significant interference under limited bandwidth. To address these challenges, in this work we formulate a novel constrained optimization problem, and propose an FL framework harnessing wireless channel perturbations and interference for improving privacy, bandwidth-efficiency, and scalability. The resultant algorithm is coined analog federated ADMM (A-FADMM) based on analog transmissions and the alternating direction method of multipliers (ADMM). In A-FADMM, all workers upload their model updates to the parameter server (PS) using a single channel via analog transmissions, during which all models are perturbed and aggregated over-the-air. This not only saves communication bandwidth, but also hides each worker’s exact model update trajectory from any eavesdropper including the honest-but-curious PS, thereby preserving data privacy against model inversion attacks. We formally prove the convergence and privacy guarantees of A-FADMM for convex functions under time-varying channels, and numerically show the effectiveness of A-FADMM under noisy channels and stochastic non-convex functions, in terms of convergence speed and scalability, as well as communication bandwidth and energy efficiency.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Federated & Distributed Learning, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

In Federated & Distributed Learning

In Privacy & Security

Citations in the corpus

Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications (2020, methodology): “However, if one aims to achieve very low loss below 10−4, A-FADMM suffers from noisy reception, and D-FADMM may, thus, be a better choice, as long as very large bandwidth and/or long uploading time are available.”
A Comprehensive Survey of Privacy-preserving Federated Learning (2021, background): “The eavesdroppers attempt to probe sensitive information by stealing the intermediate training updates or the final model transmitted between participants and the server [45, 224].”
Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM (2020, methodology): “In (Elgabli et al., 2020b), a stochastic quantization is applied for reducing the communication payload size.”
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications (2021, methodology): “The resulting inherent noisy model aggregation scheme can limit the privacy disclosure of local datasets at the edge server for free while keeping the learning performance unchanged [166], [41].”