FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering

• URL: http://arxiv.org/abs/2607.04170v1
• Date: Sun, 05 Jul 2026 08:33:38 GMT
• Title: FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering
• Abstract summary: We propose Federated learning with Frequency-domain Filtering of SAM perturbations (FedFFT)<n>FedFFT is a lightweight and plug-and-play method that filters out low-frequency components of SAM perturbations without requiring additional communication.
• Score: 23.709933555412757
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training. Sharpness-Aware Minimization (SAM) has emerged as a promising approach to improve generalization, yet its application in federated learning still suffers from divergence problems, since perturbations are computed locally and reflect client-specific loss geometries. To better understand this issue, we provide experimental evidence from a new perspective, the frequency domain, for SAM perturbations in federated settings, revealing that inter-client perturbation inconsistencies are predominantly concentrated in the low-frequency spectrum. Motivated by this insight, we propose Federated learning with Frequency-domain Filtering of SAM perturbations (FedFFT). It is a lightweight and plug-and-play method that filters out low-frequency components of SAM perturbations without requiring additional communication, thereby suppressing inconsistent components in client updates while preserving consistent learning signals. Extensive experiments across multiple benchmarks and diverse backbones demonstrate that FedFFT consistently outperforms SAM-based FL methods, particularly under severe non-IID distributions. These results highlight the effectiveness, scalability, and general applicability of our frequency-domain perspective for sharpness-aware federated optimization.

Related papers

• Full spectrum Unlearnable Examples via Spectral Equalization [29.22443621401928]
  We propose Full-spectrum Unlearnable examples via Spectral Equalization (FUSE)<n>FUSE generates spectrum-agnostic perturbations by equalizing the contributions from different bands and enforcing cross-band consistency.<n>Experiments across multiple datasets, architectures, and spectral filtering demonstrate the strong protection achieved by FUSE.
  arXiv  Detail & Related papers  (2026-06-25T07:53:53Z)
• FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning [65.74073318961548]
  Sharpness-aware (SAM) is an effective method for improving the generalization of federated learning (FL) by steering local training toward flat minima.<n>We propose Federated Learning with minimization-suppressed sharpness-suppressed search (FedVSSAM)<n>FedVSSAM anchors both update directions to a more stable global direction and uses it consistently in local flatness perturbation, local update.
  arXiv  Detail & Related papers  (2026-05-09T20:03:02Z)
• FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels [2.0878272814614087]
  Federated learning (FL) enables collaborative model training without sharing raw data.<n>The presence of noisy labels across distributed clients can severely degrade the learning performance.<n>We propose FedSIR, a multi-stage framework for robust FL under noisy labels.
  arXiv  Detail & Related papers  (2026-04-22T17:49:20Z)
• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments [0.0]
  Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy.<n> statistical heterogeneity among clients, often manifested as non-IID label distributions, poses significant challenges to convergence and generalization.<n>We propose textbfFedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation), a novel algorithm that dynamically adjusts the SAM perturbation radius and aggregation weights based on client-specific heterogeneity scores.
  arXiv  Detail & Related papers  (2025-12-29T19:42:50Z)
• Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization [81.32266996009575]
  In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima. We propose FedLESAM, a novel algorithm that locally estimates the direction of global perturbation on client side.
  arXiv  Detail & Related papers  (2024-05-29T08:46:21Z)
• Friendly Sharpness-Aware Minimization [62.57515991835801]
  Sharpness-Aware Minimization (SAM) has been instrumental in improving deep neural network training by minimizing both training loss and loss sharpness. We investigate the key role of batch-specific gradient noise within the adversarial perturbation, i.e., the current minibatch gradient. By decomposing the adversarial gradient noise components, we discover that relying solely on the full gradient degrades generalization while excluding it leads to improved performance.
  arXiv  Detail & Related papers  (2024-03-19T01:39:33Z)
• FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation [95.85026305874824]
  We introduce a data-driven approach called FedSkip to improve the client optima by periodically skipping federated averaging and scattering local models to the cross devices. We conduct extensive experiments on a range of datasets to demonstrate that FedSkip achieves much higher accuracy, better aggregation efficiency and competing communication efficiency.
  arXiv  Detail & Related papers  (2022-12-14T13:57:01Z)
• FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning [91.74206675452888]
  We propose a novel method FedFM, which guides each client's features to match shared category-wise anchors. To achieve higher efficiency and flexibility, we propose a FedFM variant, called FedFM-Lite, where clients communicate with server with fewer synchronization times and communication bandwidth costs.
  arXiv  Detail & Related papers  (2022-10-14T08:11:34Z)
• FedPrune: Towards Inclusive Federated Learning [1.308951527147782]
  Federated learning (FL) is a distributed learning technique that trains a shared model over distributed data in a privacy-preserving manner. We propose FedPrune; a system that tackles this challenge by pruning the global model for slow clients based on their device characteristics. By using insights from Central Limit Theorem, FedPrune incorporates a new aggregation technique that achieves robust performance over non-IID data.
  arXiv  Detail & Related papers  (2021-10-27T06:33:38Z)

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.