SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity

• URL: http://arxiv.org/abs/2607.04189v1
• Date: Sun, 05 Jul 2026 09:23:35 GMT
• Title: SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity
• Abstract summary: Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that hampers global convergence.<n>In this work, we revisit client drift from a novel frequency-domain perspective and uncover a critical Spectral Bias of Drift.<n>Motivated by this, we propose SpecGradFilter, a unified Spectral Filtering Gradient Framework that tames heterogeneity by suppressing discordant low-frequency signals.
• Score: 57.84199526590779
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that severely hampers global convergence. While existing approaches attempt to mitigate this drift through spatial-domain gradient correction or regularization, they overlook the intrinsic spectral structure of optimization signals. In this work, we revisit client drift from a novel frequency-domain perspective and uncover a critical Spectral Bias of Drift: inter-client gradient divergence is predominantly concentrated in low-frequency components which encode client-specific distributional shifts, while high-frequency components representing fine-grained features remain relatively consistent. Motivated by this, we propose SpecGradFilter, a unified Spectral Gradient Filtering Framework that tames heterogeneity by suppressing discordant low-frequency signals. Crucially, we demonstrate that SpecGradFilter is a generalizable principle, effective not only via precise FFT-based truncation but also through spatial approximations like Gaussian detrending. Extensive experiments on benchmarks such as CIFAR-10/100 and Tiny-ImageNet demonstrate that SpecGradFilter significantly performs better performance in highly Non-IID settings with negligible communication overhead, establishing a new paradigm for robust 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)
• Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs [59.973833105841685]
  A key challenge for improving adversarial transferability is to effectively capture the intrinsic visual focus shared across different models.<n>We propose FRA-Attack, which addresses both challenges from a unified frequency-domain regularization perspective.<n>For feature alignment, a high-pass DCT objective on patch features suppresses redundant global structures and concentrates the loss on the high-frequency band that carries the MLLMs' intrinsic visual focus.<n>For gradient optimization, we introduce Frequency-domain Gradient Regularization (FGR), a textitmodel-agnostic low-pass regularizer that modulates the surrogate gradient using
  arXiv  Detail & Related papers  (2026-05-20T08:15:56Z)
• UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment [20.399005485708273]
  Device-free localization trains models from heterogeneous wireless and visual sensors distributed across edge devices.<n>We propose UMEDA, a graph federated learning framework in which clients form nodes of a global graph that share a continuous integral operator.<n> UMEDA outperforms state-of-the-art federated baselines in accuracy, convergence, and communication efficiency.
  arXiv  Detail & Related papers  (2026-05-08T08:15:47Z)
• Physics-Aligned Spectral Mamba: Decoupling Semantics and Dynamics for Few-Shot Hyperspectral Target Detection [14.607792636586067]
  SpecMamba is a framework that decouples stable semantic representation from agile spectral adaptation.<n>It consistently outperforms state-of-the-art methods in detection accuracy and cross-domain generalization.
  arXiv  Detail & Related papers  (2026-04-07T08:04:18Z)
• Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization [56.95448807869383]
  Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning.<n>Recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage.<n>We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD)
  arXiv  Detail & Related papers  (2026-04-01T14:32:15Z)
• Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy [1.5766082819987293]
  We introduce the FFT-Enhanced Kalman Filter (FFTKF), a differentially private optimization method that improves gradient quality.<n>FFTKF applies frequency-domain filtering to shift privacy noise into less informative high-frequency components.<n>It achieves higher test accuracy than DP-SGD and DiSK on MNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet with CNNs, Wide ResNets, and Vision Transformers.
  arXiv  Detail & Related papers  (2025-05-07T14:38:58Z)
• Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection [59.042018542376596]
  Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors.<n>Anomaly-Aware Pre-Training and Fine-Tuning (APF) is a framework to mitigate the challenges in GAD.<n> Comprehensive experiments on 10 benchmark datasets validate the superior performance of APF in comparison to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-19T09:57:35Z)
• Understanding Dataset Distillation via Spectral Filtering [69.07076441512612]
  We introduce UniDD, a spectral filtering framework that unifies diverse DD objectives.<n>UniDD reveals that the essence of DD fundamentally lies in matching frequency-specific features.<n>To address this limitation, we propose Curriculum Frequency Matching (CFM), which gradually adjusts the filter parameter to cover both low- and high-frequency information.
  arXiv  Detail & Related papers  (2025-03-03T06:22:34Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• Graph Federated Learning for CIoT Devices in Smart Home Applications [23.216140264163535]
  We propose a novel Graph Signal Processing (GSP)-inspired aggregation rule based on graph filtering dubbed G-Fedfilt'' The proposed aggregator enables a structured flow of information based on the graph's topology. It is capable of yielding up to $2.41%$ higher accuracy than FedAvg in the case of testing the generalization of the models.
  arXiv  Detail & Related papers  (2022-12-29T17:57:19Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)

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.