ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gulati, Mayank, Groß, Benedikt, Wunder, Gerhard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909963086987264
author Gulati, Mayank
Groß, Benedikt
Wunder, Gerhard
author_facet Gulati, Mayank
Groß, Benedikt
Wunder, Gerhard
contents We present ALIGN-FL, a novel approach to distributed learning that addresses the challenge of learning from highly disjoint data distributions through selective sharing of generative components. Instead of exchanging full model parameters, our framework enables privacy-preserving learning by transferring only generative capabilities across clients, while the server performs global training using synthetic samples. Through complementary privacy mechanisms: DP-SGD with adaptive clipping and Lipschitz regularized VAE decoders and a stateful architecture supporting heterogeneous clients, we experimentally validate our approach on MNIST and Fashion-MNIST datasets with cross-domain outliers. Our analysis demonstrates that both privacy mechanisms effectively map sensitive outliers to typical data points while maintaining utility in extreme Non-IID scenarios typical of cross-silo collaborations. Index Terms: Client-invariant Learning, Federated Learning (FL), Privacy-preserving Generative Models, Non-Independent and Identically Distributed (Non-IID), Heterogeneous Architectures
format Preprint
id arxiv_https___arxiv_org_abs_2512_13316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
Gulati, Mayank
Groß, Benedikt
Wunder, Gerhard
Machine Learning
Artificial Intelligence
We present ALIGN-FL, a novel approach to distributed learning that addresses the challenge of learning from highly disjoint data distributions through selective sharing of generative components. Instead of exchanging full model parameters, our framework enables privacy-preserving learning by transferring only generative capabilities across clients, while the server performs global training using synthetic samples. Through complementary privacy mechanisms: DP-SGD with adaptive clipping and Lipschitz regularized VAE decoders and a stateful architecture supporting heterogeneous clients, we experimentally validate our approach on MNIST and Fashion-MNIST datasets with cross-domain outliers. Our analysis demonstrates that both privacy mechanisms effectively map sensitive outliers to typical data points while maintaining utility in extreme Non-IID scenarios typical of cross-silo collaborations. Index Terms: Client-invariant Learning, Federated Learning (FL), Privacy-preserving Generative Models, Non-Independent and Identically Distributed (Non-IID), Heterogeneous Architectures
title ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.13316