No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

TL;DR

This paper investigates how data heterogeneity affects deep classification models in federated learning, revealing a bias in classifiers and proposing a simple calibration method that improves performance on standard benchmarks.

Contribution

It provides a detailed analysis of layer representations in federated models and introduces CCVR, a novel classifier calibration algorithm for non-IID data.

Findings

Classifier bias is greater than other layers in federated models.

Post-calibration significantly improves classification performance.

CCVR achieves state-of-the-art results on CIFAR-10, CIFAR-100, and CINIC-10.

Abstract

A central challenge in training classification models in the real-world federated system is learning with non-IID data. To cope with this, most of the existing works involve enforcing regularization in local optimization or improving the model aggregation scheme at the server. Other works also share public datasets or synthesized samples to supplement the training of under-represented classes or introduce a certain level of personalization. Though effective, they lack a deep understanding of how the data heterogeneity affects each layer of a deep classification model. In this paper, we bridge this gap by performing an experimental analysis of the representations learned by different layers. Our observations are surprising: (1) there exists a greater bias in the classifier than other layers, and (2) the classification performance can be significantly improved by post-calibrating the classifier after federated training. Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model. Experimental results demonstrate that CCVR achieves state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10. We hope that our simple yet effective method can shed some light on the future research of federated learning with non-IID data.