Recurrent early exits for federated learning with heterogeneous clients

R. Lee*, J. Fernandez-Marques, S. X. Hu, D. Li, S. Laskaridis, Ł. Dudziak, Timothy Hospedales, F. Huszar, N. D. Lane

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clients with varying hardware capacities; clients have differing compute and memory requirements. To tackle this challenge, recent state-of-the-art approaches leverage the use of early exits. Nonetheless, these approaches fall short of mitigating the challenges of joint learning multiple exit classifiers, often relying on hand-picked heuristic solutions for knowledge distillation among classifiers and/or utilizing additional layers for weaker classifiers. In this work, instead of utilizing multiple classifiers, we propose a recurrent early exit approach named ReeFL that fuses features from different sub-models into a single shared classifier. Specifically, we use a transformer-based early exit module shared among sub-models to i) better exploit multi-layer feature representations for task-specific prediction and ii) modulate the feature representation of the backbone model for subsequent predictions. We additionally present a per-client self-distillation approach where the best sub-model is automatically selected as the teacher of the other sub-models at each client. Our experiments on standard image and speech classification benchmarks across various emerging federated fine-tuning baselines demonstrate ReeFL’s effectiveness over previous works.
Original languageEnglish
Title of host publicationProceedings of the 41st International Conference on Machine Learning
Publication statusAccepted/In press - 15 May 2024
EventThe 41st International Conference on Machine Learning - Vienna, Austria
Duration: 21 Jul 202427 Jul 2024
https://icml.cc/

Conference

ConferenceThe 41st International Conference on Machine Learning
Abbreviated titleICML 2024
Country/TerritoryAustria
CityVienna
Period21/07/2427/07/24
Internet address

Fingerprint

Dive into the research topics of 'Recurrent early exits for federated learning with heterogeneous clients'. Together they form a unique fingerprint.

Cite this