SphereFed: Hyperspherical Federated Learning

TL;DR

SphereFed introduces a hyperspherical representation constraint in federated learning to effectively handle non-i.i.d. data, improving accuracy and efficiency across diverse datasets and models.

Contribution

This work proposes a novel hyperspherical federated learning framework that constrains data representations to a shared unit hypersphere, addressing non-i.i.d. data challenges.

Findings

Improves federated learning accuracy by up to 6% on challenging datasets.

Enhances computation and communication efficiency.

Effective calibration of classifiers without direct data access.

Abstract

Federated Learning aims at training a global model from multiple decentralized devices (i.e. clients) without exchanging their private local data. A key challenge is the handling of non-i.i.d. (independent identically distributed) data across multiple clients that may induce disparities of their local features. We introduce the Hyperspherical Federated Learning (SphereFed) framework to address the non-i.i.d. issue by constraining learned representations of data points to be on a unit hypersphere shared by clients. Specifically, all clients learn their local representations by minimizing the loss with respect to a fixed classifier whose weights span the unit hypersphere. After federated training in improving the global model, this classifier is further calibrated with a closed-form solution by minimizing a mean squared loss. We show that the calibration solution can be computed efficiently and distributedly without direct access of local data. Extensive experiments indicate that our SphereFed approach is able to improve the accuracy of multiple existing federated learning algorithms by a considerable margin (up to 6% on challenging datasets) with enhanced computation and communication efficiency across datasets and model architectures.