arXiv Machine Learning July 7, 2026 By Liyang Yuan, Yibo Yang, Dandan Guo, Peter Richtarik, Zhouchen Lin

SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity

Read the original on arXiv Machine Learning →

arXiv:2607. 04189v1 Announce Type: new 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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 7

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

arXiv:2607. 04170v1 Announce Type: new 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.

By Liyang Yuan, Yibo Yang, Dandan Guo

benchmarks

arXiv Machine Learning

Jun 15

Federated Learning for Feature Generalization with Convex Constraints

arXiv:2606. 14416v1 Announce Type: new Abstract: Federated learning (FL) often struggles with generalization due to heterogeneous client data.

By Dongwon Kim, Donghee Kim, Sung Kuk Shyn, Kwangsu Kim

benchmarks

arXiv Machine Learning

Jun 16

Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning

arXiv:2512. 12737v2 Announce Type: replace Abstract: Decentralized federated learning (DFL) enables collaborative model training without a central server, but converges slowly under statistical heterogeneity.

By Li Xia

data-engineering

arXiv Machine Learning

Jul 9

Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer

arXiv:2501. 10870v2 Announce Type: replace-cross Abstract: The principal objective of this work is twofold within nonparametric regression settings: (1) to establish the minimax optimal convergence rates for fixed-bandwidth Gaussian kernel spectral algorithms when the true regression function resides in a Sobolev space, and (2) to apply Gaussian spectral algorithms for achieving robust and adaptive transfer learning under concept shift.

By Haotian Lin, Matthew Reimherr

fine-tuning

arXiv Machine Learning

Jul 13

Spectrally Deconfounded Gradient Boosting

arXiv:2607. 09371v1 Announce Type: cross Abstract: Flexible machine-learning methods can be sensitive to hidden confounding: they may learn associations induced by unobserved confounders rather than stable signals.

By Andrea Nava, Peter B\"uhlmann, Fabio Sigrist

arXiv AI

Jul 9

FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning

arXiv:2512. 02076v2 Announce Type: replace-cross Abstract: We propose FDRMFL, a task-driven multimodal feature extraction framework for federated regression under non-IID data distributions.

By Haozhe Wu

multimodal benchmarks

Related stories

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

Federated Learning for Feature Generalization with Convex Constraints

Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning

Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer

Spectrally Deconfounded Gradient Boosting

FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning