paper-with-me

홈 › Papers

The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics

2026-02-01 · Fabio Turazza, Marco Picone, Marco Mamei arxiv

Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high communication costs and privacy risks from repeated model transmissions. In contrast, one-shot federated learning (OFL) alleviates these limitations by reducing communication to a single round, thereby lowering overhead and enhancing practical deployability. Nevertheless, most existing one-shot approaches remain either impractical or constrained, for example, they often depend on the availability of a public dataset, assume homogeneous client models, or require uploading additional data or model information. To overcome these issues, we introduce the Gaussian-Head OFL (GH-OFL) family, a suite of one-shot federated methods that assume class-conditional Gaussianity of pretrained embeddings. Clients transmit only sufficient statistics (per-class counts and first/second-order moments) and the server builds heads via three components: (i) Closed-form Gaussian heads (NB/LDA/QDA) computed directly from the received statistics; (ii) FisherMix, a linear head with cosine margin trained on synthetic samples drawn in an estimated Fisher subspace; and (iii) Proto-Hyper, a lightweight low-rank residual head that refines Gaussian logits via knowledge distillation on those synthetic samples. In our experiments, GH-OFL methods deliver state-of-the-art robustness and accuracy under strong non-IID skew while remaining strictly data-free.

📄 PDF Abstract BibTeX arXiv:2602.01186

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationFederated Learning

Similar Papers 제목 키워드 기반

Parametric Feature Transfer: One-shot Federated Learning with Foundation Models

2024-02-02 · Mahdi Beitollahi, Alex Bie, Sobhan Hemati, Leo Maxime Brunswic 외

In one-shot federated learning (FL), clients collaboratively train a global model in a single round of communication. Existing approaches for one-shot FL enhance communication efficiency at the expense of diminished accu…

Federated Learning

Personalized Federated Learning via Gaussian Generative Modeling

2026-03-12 · Peng Hu, Jianwei Ma arxiv

Federated learning has emerged as a paradigm to train models collaboratively on inherently distributed client data while safeguarding privacy. In this context, personalized federated learning tackles the challenge of dat…

Personalized Federated LearningRepresentation LearningBayesian Inference

Federated $f$-Differential Privacy

2021-02-22 · Qinqing Zheng, Shuxiao Chen, Qi Long, Weijie J. Su

Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we in…

Federated Learning

Zero-Shot Decentralized Federated Learning

2025-09-30 · Alessio Masano, Matteo Pennisi, Federica Proietto Salanitri, Concetto Spampinato 외 arxiv

CLIP has revolutionized zero-shot learning by enabling task generalization without fine-tuning. While prompting techniques like CoOp and CoCoOp enhance CLIP's adaptability, their effectiveness in Federated Learning (FL) …

Image ClassificationFederated LearningZero-Shot Learning

One-Shot Federated Learning with Classifier-Free Diffusion Models

2025-02-12 · Obaidullah Zaland, Shutong Jin, Florian T. Pokorny, Monowar Bhuyan

Federated learning (FL) enables collaborative learning without data centralization but introduces significant communication costs due to multiple communication rounds between clients and the server. One-shot federated le…

BenchmarkingDataset GenerationFederated Learning