FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts

• URL: http://arxiv.org/abs/2511.22305v1
• Date: Thu, 27 Nov 2025 10:36:08 GMT
• Title: FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
• Authors: Dario Fenoglio, Mohan Li, Pietro Barbiero, Nicholas D. Lane, Marc Langheinrich, Martin Gjoreski,
• Abstract summary: Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy.<n>FLUX is a novel clustering-based FL framework that addresses the four most common types of distribution shifts during both training and test time.
• Score: 24.415282689834985
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are independent and identically distributed (IID). However, when this assumption does not hold, the global model accuracy may drop significantly, limiting FL applicability in real-world scenarios. To address this gap, we propose FLUX, a novel clustering-based FL (CFL) framework that addresses the four most common types of distribution shifts during both training and test time. To this end, FLUX leverages privacy-preserving client-side descriptor extraction and unsupervised clustering to ensure robust performance and scalability across varying levels and types of distribution shifts. Unlike existing CFL methods addressing non-IID client distribution shifts, FLUX i) does not require any prior knowledge of the types of distribution shifts or the number of client clusters, and ii) supports test-time adaptation, enabling unseen and unlabeled clients to benefit from the most suitable cluster-specific models. Extensive experiments across four standard benchmarks, two real-world datasets and ten state-of-the-art baselines show that FLUX improves performance and stability under diverse distribution shifts, achieving an average accuracy gain of up to 23 percentage points over the best-performing baselines, while maintaining computational and communication overhead comparable to FedAvg.

Related papers

• Federated Learning with Profile Mapping under Distribution Shifts and Drifts [13.33580160559305]
  Federated Learning (FL) enables decentralized model training across clients without sharing raw data.<n>Existing methods often fail to address distribution shift across clients and distribution drift over time.<n>We introduce Feroma, a novel FL framework that explicitly handles both distribution shift and drift without relying on client or cluster identity.
  arXiv  Detail & Related papers  (2026-02-07T19:31:50Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• Federated Learning Clients Clustering with Adaptation to Data Drifts [27.974937897248132]
  Federated Learning (FL) trains deep models across edge devices without centralizing raw data, preserving user privacy.<n>We propose FIELDING, a framework for handling diverse types of data drift with low overhead.<n>Experiments show that FIELDING improves final model accuracy by 1.9-5.9% and achieves target accuracy 1.16x-2.23x faster than existing state-of-the-art CFL methods.
  arXiv  Detail & Related papers  (2024-11-03T14:13:38Z)
• FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering [28.057411252785176]
  Federated learning (FL) is an emerging distributed machine learning paradigm enabling collaborative model training on decentralized devices without exposing their local data. This paper proposes FedClust, a novel CFL approach leveraging correlations between local model weights and client data distributions.
  arXiv  Detail & Related papers  (2024-03-07T01:50:36Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [55.0981921695672]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm.<n>It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities.<n>It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning [9.975023463908496]
  Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. We propose a novel regularization technique based on adaptive self-distillation (ASD) for training models on the client side. Our regularization scheme adaptively adjusts to the client's training data based on the global model entropy and the client's label distribution.
  arXiv  Detail & Related papers  (2023-05-31T07:00:42Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• FL Games: A Federated Learning Framework for Distribution Shifts [71.98708418753786]
  Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. We propose FL GAMES, a game-theoretic framework for federated learning that learns causal features that are invariant across clients.
  arXiv  Detail & Related papers  (2022-10-31T22:59:03Z)
• Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces [59.33965805898736]
  Clustered learning has been shown to produce promising results by grouping clients into clusters. Existing FL algorithms are essentially trying to group clients together with similar distributions. Prior FL algorithms attempt similarities indirectly during training.
  arXiv  Detail & Related papers  (2022-09-21T17:37:54Z)
• Gradient Masked Averaging for Federated Learning [24.687254139644736]
  Federated learning allows a large number of clients with heterogeneous data to coordinate learning of a unified global model. Standard FL algorithms involve averaging of model parameters or gradient updates to approximate the global model at the server. We propose a gradient masked averaging approach for FL as an alternative to the standard averaging of client updates.
  arXiv  Detail & Related papers  (2022-01-28T08:42:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.