mlsanityData to 14 Oct 2026

From Optimization to Generalization: Fair Federated Learning against Quality Shift via Inter-Client Sharpness Matching

arXiv 2404.17805 ↗First posted 27 Apr 2024cs.LG cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Due to escalating privacy concerns, federated learning has been recognized as a vital approach for training deep neural networks with decentralized medical data. In practice, it is challenging to ensure consistent imaging quality across various institutions, often attributed to equipment malfunctions affecting a minority of clients. This imbalance in image quality can cause the federated model to develop an inherent bias towards higher-quality images, thus posing a severe fairness issue. In this study, we pioneer the identification and formulation of this new fairness challenge within the context of the imaging quality shift. Traditional methods for promoting fairness in federated learning predominantly focus on balancing empirical risks across diverse client distributions. This strategy primarily facilitates fair optimization across different training data distributions, yet neglects the crucial aspect of generalization. To address this, we introduce a solution termed Federated learning with Inter-client Sharpness Matching (FedISM). FedISM enhances both local training and global aggregation by incorporating sharpness-awareness, aiming to harmonize the sharpness levels across clients for fair generalization. Our empirical evaluations, conducted using the widely-used ICH and ISIC 2019 datasets, establish FedISM's superiority over current state-of-the-art federated learning methods in promoting fairness. Code is available at https://github.com/wnn2000/FFL4MIA.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 27 Apr 2024.

Builds on

31 of 40 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  4. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  6. 2020Long-tail learning via logit adjustmentcited by 618
  7. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  8. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  9. 2019Agnostic Federated Learningcited by 456
  10. 2019Fair Resource Allocation in Federated Learningcited by 394
  11. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  12. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 225
19 more
  1. 2022Surrogate Gap Minimization Improves Sharpness-Aware Trainingcited by 172
  2. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  3. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  4. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 118
  5. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  6. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  7. 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
  8. 2020Collaborative Fairness in Federated Learningcited by 95
  9. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 52
  10. 2023Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscapecited by 46
  11. 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 40
  12. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  13. 2023ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognitioncited by 31
  14. 2023Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimizationcited by 29
  15. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  16. 2022IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentationcited by 22
  17. 2022FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classificationcited by 18
  18. 2023FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noisecited by 14
  19. 2022Dynamic Bank Learning for Semi-supervised Federated Image Diagnosis with Class Imbalancecited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2024FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneitycited by 5
  2. 2024FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completenesscited by 2
  3. 2025FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysiscited by 2
  4. 2025Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State Matchingcited by 0
  5. 2026Federated Learning at the Forefront of Fairness: A Multifaceted Perspectivecited by 0