Equitable Federated Learning with Activation Clustering
Not on the map. Why?
Abstract (arXiv)
Federated learning is a prominent distributed learning paradigm that incorporates collaboration among diverse clients, promotes data locality, and thus ensures privacy. These clients have their own technological, cultural, and other biases in the process of data generation. However, the present standard often ignores this bias/heterogeneity, perpetuating bias against certain groups rather than mitigating it. In response to this concern, we propose an equitable clustering-based framework where the clients are categorized/clustered based on how similar they are to each other. We propose a unique way to construct the similarity matrix that uses activation vectors. Furthermore, we propose a client weighing mechanism to ensure that each cluster receives equal importance and establish O(1/√K) rate of convergence to reach an ε-stationary solution. We assess the effectiveness of our proposed strategy against common baselines, demonstrating its efficacy in terms of reducing the bias existing amongst various client clusters and consequently ameliorating algorithmic bias against specific groups.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 24 Oct 2024.
Builds on
30 of 44 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2018LEAF: A Benchmark for Federated Settingscited by 780
- 2021Model-Contrastive Federated Learningcited by 762
- 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
- 2021Federated Learning Based on Dynamic Regularizationcited by 555
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2019Agnostic Federated Learningcited by 451
18 more
- 2019Fair Resource Allocation in Federated Learningcited by 389
- 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
- 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
- 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
- 2020Collaborative Fairness in Federated Learningcited by 95
- 2018SGD and Hogwild! Convergence Without the Bounded Gradients Assumptioncited by 94
- 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
- 2018Bias Mitigation Post-processing for Individual and Group Fairnesscited by 72
- 2019Active Federated Learningcited by 63
- 2021Federated Learning with Fair Averagingcited by 59
- 2020Faster Non-Convex Federated Learning via Global and Local Momentumcited by 48
- 2023Improving the Model Consistency of Decentralized Federated Learningcited by 45
- 2022Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspacescited by 36
- 2021GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learningcited by 21
- 2023On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharingcited by 16
- 2023Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noisecited by 4
- 2024Submodular Maximization Approaches for Equitable Client Selection in Federated Learningcited by 1
Built on by
Not cited yet.