Fed-BAC: Federated Bandit-Guided Additive Clustering in Hierarchical Federated Learning

2026-05-12 · Satwat Bashir, Tasos Dagiuklas, Muddesar Iqbal arxiv

Hierarchical federated learning (HFL) leverages edge servers for partial aggregation in edge computing. Yet existing FL methods lack mechanisms for jointly optimizing cluster assignment and client selection under data heterogeneity. This paper proposes Fed-BAC, which integrates additive cluster personalization with a two-level bandit framework: contextual bandits at the cloud learn server-to-cluster assignments, while Thompson Sampling at each edge server identifies high-contributing clients. The additive decomposition enables the sharing of knowledge between groups through a globally aggregated network, while cluster-specific networks capture distribution variations. Across three classification benchmarks (CIFAR-10, SVHN, Fashion-MNIST) under moderate ($α= 0.5$) and severe ($α= 0.1$) Dirichlet non-IID partitioning, Fed-BAC achieves distributed accuracy gains of up to +35.5pp over HierFAVG and +8.4pp over IFCA, while requiring only 80% client participation, converging 1.5 to 4.8$\times$ faster depending on dataset and accuracy target, and improving cross-server fairness. These gains are further validated at 5$\times$ deployment scale on CIFAR-10. The advantage of Fed-BAC increases with heterogeneity severity, confirming that additive cluster personalization becomes increasingly valuable as data distributions diverge.

📄 PDF Abstract BibTeX arXiv:2605.11815

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Federated Online Clustering of Bandits

2022-08-31 · Xutong Liu, Haoru Zhao, Tong Yu, Shuai Li 외

Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems. A line of works, called the clustering of bandits (CLUB), utilize the collaborative effect over users and …

Clustering Decision Making Online Clustering Recommendation Systems+1

Hierarchical Bayesian Bandits

2021-11-12 · Joey Hong, Branislav Kveton, Manzil Zaheer, Mohammad Ghavamzadeh

Meta-, multi-task, and federated learning can be all viewed as solving similar tasks, drawn from a distribution that reflects task similarities. We provide a unified view of all these problems, as learning to act in a hi…

Federated Learning Thompson Sampling

On the Price of Differential Privacy for Hierarchical Clustering

2025-04-22 · Chengyuan Deng, Jie Gao, Jalaj Upadhyay, Chen Wang 외

Hierarchical clustering is a fundamental unsupervised machine learning task with the aim of organizing data into a hierarchy of clusters. Many applications of hierarchical clustering involve sensitive user information, t…

Clustering Privacy Preserving

Federated X-Armed Bandit

2022-05-30 · Wenjie Li, Qifan Song, Jean Honorio, Guang Lin

This work establishes the first framework of federated $\mathcal{X}$-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figur…

Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees

2023-01-31 · Jacob Imola, Alessandro Epasto, Mohammad Mahdian, Vincent Cohen-Addad 외

Hierarchical Clustering is a popular unsupervised machine learning method with decades of history and numerous applications. We initiate the study of differentially private approximation algorithms for hierarchical clust…

Clustering Stochastic Block Model