English

FEATHERS: Federated Architecture and Hyperparameter Search

Machine Learning 2023-03-28 v3

Abstract

Deep neural architectures have profound impact on achieved performance in many of today's AI tasks, yet, their design still heavily relies on human prior knowledge and experience. Neural architecture search (NAS) together with hyperparameter optimization (HO) helps to reduce this dependence. However, state of the art NAS and HO rapidly become infeasible with increasing amount of data being stored in a distributed fashion, typically violating data privacy regulations such as GDPR and CCPA. As a remedy, we introduce FEATHERS - FE\textbf{FE}derated A\textbf{A}rchiT\textbf{T}ecture and H\textbf{H}ypER\textbf{ER}parameter S\textbf{S}earch, a method that not only optimizes both neural architectures and optimization-related hyperparameters jointly in distributed data settings, but further adheres to data privacy through the use of differential privacy (DP). We show that FEATHERS efficiently optimizes architectural and optimization-related hyperparameters alike, while demonstrating convergence on classification tasks at no detriment to model performance when complying with privacy constraints.

Keywords

Cite

@article{arxiv.2206.12342,
  title  = {FEATHERS: Federated Architecture and Hyperparameter Search},
  author = {Jonas Seng and Pooja Prasad and Martin Mundt and Devendra Singh Dhami and Kristian Kersting},
  journal= {arXiv preprint arXiv:2206.12342},
  year   = {2023}
}

Comments

Main paper: 8 pages, References: 2 pages, Supplement: 4.5 pages, Main paper: 3 figures, 2 tables, 1 algorithm, Supplement: 2 figure, 4 algorithms, extended previous version by Differential Privacy, theoretical results and more experiments. Updated author list as it was incomplete

R2 v1 2026-06-24T12:03:13.351Z