Saved in:
Bibliographic Details
Main Authors: Zaland, Obaidullah, Jin, Shutong, Pokorny, Florian T., Bhuyan, Monowar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.08488
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910004664074240
author Zaland, Obaidullah
Jin, Shutong
Pokorny, Florian T.
Bhuyan, Monowar
author_facet Zaland, Obaidullah
Jin, Shutong
Pokorny, Florian T.
Bhuyan, Monowar
contents 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 learning (OSFL) addresses this by forming a global model with a single communication round, often relying on the server's model distillation or auxiliary dataset generation - mostly through pre-trained diffusion models (DMs). Existing DM-assisted OSFL methods, however, typically employ classifier-guided DMs, which require training auxiliary classifier models at each client, introducing additional computation overhead. This work introduces OSCAR (One-Shot Federated Learning with Classifier-Free Diffusion Models), a novel OSFL approach that eliminates the need for auxiliary models. OSCAR uses foundation models to devise category-specific data representations at each client which are integrated into a classifier-free diffusion model pipeline for server-side data generation. In our experiments, OSCAR outperforms the state-of-the-art on four benchmark datasets while reducing the communication load by at least 99%.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08488
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One-Shot Federated Learning with Classifier-Free Diffusion Models
Zaland, Obaidullah
Jin, Shutong
Pokorny, Florian T.
Bhuyan, Monowar
Machine Learning
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 learning (OSFL) addresses this by forming a global model with a single communication round, often relying on the server's model distillation or auxiliary dataset generation - mostly through pre-trained diffusion models (DMs). Existing DM-assisted OSFL methods, however, typically employ classifier-guided DMs, which require training auxiliary classifier models at each client, introducing additional computation overhead. This work introduces OSCAR (One-Shot Federated Learning with Classifier-Free Diffusion Models), a novel OSFL approach that eliminates the need for auxiliary models. OSCAR uses foundation models to devise category-specific data representations at each client which are integrated into a classifier-free diffusion model pipeline for server-side data generation. In our experiments, OSCAR outperforms the state-of-the-art on four benchmark datasets while reducing the communication load by at least 99%.
title One-Shot Federated Learning with Classifier-Free Diffusion Models
topic Machine Learning
url https://arxiv.org/abs/2502.08488