Bias-Eliminating Augmentation Learning for Debiased Federated Learning
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 20442-20452
Abstract
Learning models trained on biased datasets tend to observe correlations between categorical and undesirable features, which result in degraded performances. Most existing debiased learning models are designed for centralized machine learning, which cannot be directly applied to distributed settings like federated learning (FL), which collects data at distinct clients with privacy preserved. To tackle the challenging task of debiased federated learning, we present a novel FL framework of Bias-Eliminating Augmentation Learning (FedBEAL), which learns to deploy Bias-Eliminating Augmenters (BEA) for producing client-specific bias-conflicting samples at each client. Since the bias types or attributes are not known in advance, a unique learning strategy is presented to jointly train BEA with the proposed FL framework. Extensive image classification experiments on datasets with various bias types confirm the effectiveness and applicability of our FedBEAL, which performs favorably against state-of-the-art debiasing and FL methods for debiased FL.Keywords
This publication has 18 references indexed in Scilit:
- Advances and Open Problems in Federated LearningFoundations and Trends in Machine Learning, 2021
- ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning2021
- Shortcut learning in deep neural networksNature Machine Intelligence, 2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- REPAIR: Removing Representation Bias by Dataset Resampling2019
- Learning Not to Learn: Training Deep Neural Networks With Biased Data2019
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- Deep Residual Learning for Image Recognition2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998