Saved in:
Bibliographic Details
Main Authors: Yashwanth, M, Nayak, Gaurav Kumar, Rangwani, Harsh, Singh, Arya, Babu, R. Venkatesh, Chakraborty, Anirban
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.08314
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914189501530112
author Yashwanth, M
Nayak, Gaurav Kumar
Rangwani, Harsh
Singh, Arya
Babu, R. Venkatesh
Chakraborty, Anirban
author_facet Yashwanth, M
Nayak, Gaurav Kumar
Rangwani, Harsh
Singh, Arya
Babu, R. Venkatesh
Chakraborty, Anirban
contents Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the locally trained models without sharing any client's training data. It has been observed in recent works that learning in a federated manner may lead the aggregated global model to converge to a 'sharp minimum' thereby adversely affecting the generalizability of this FL-trained model. Therefore, in this work, we aim to improve the generalization performance of models trained in a federated setup by introducing a 'flatness' constrained FL optimization problem. This flatness constraint is imposed on the top eigenvalue of the Hessian computed from the training loss. As each client trains a model on its local data, we further re-formulate this complex problem utilizing the client loss functions and propose a new computationally efficient regularization technique, dubbed 'MAN,' which Minimizes Activation's Norm of each layer on client-side models. We also theoretically show that minimizing the activation norm reduces the top eigenvalue of the layer-wise Hessian of the client's loss, which in turn decreases the overall Hessian's top eigenvalue, ensuring convergence to a flat minimum. We apply our proposed flatness-constrained optimization to the existing FL techniques and obtain significant improvements, thereby establishing new state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08314
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning
Yashwanth, M
Nayak, Gaurav Kumar
Rangwani, Harsh
Singh, Arya
Babu, R. Venkatesh
Chakraborty, Anirban
Machine Learning
Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the locally trained models without sharing any client's training data. It has been observed in recent works that learning in a federated manner may lead the aggregated global model to converge to a 'sharp minimum' thereby adversely affecting the generalizability of this FL-trained model. Therefore, in this work, we aim to improve the generalization performance of models trained in a federated setup by introducing a 'flatness' constrained FL optimization problem. This flatness constraint is imposed on the top eigenvalue of the Hessian computed from the training loss. As each client trains a model on its local data, we further re-formulate this complex problem utilizing the client loss functions and propose a new computationally efficient regularization technique, dubbed 'MAN,' which Minimizes Activation's Norm of each layer on client-side models. We also theoretically show that minimizing the activation norm reduces the top eigenvalue of the layer-wise Hessian of the client's loss, which in turn decreases the overall Hessian's top eigenvalue, ensuring convergence to a flat minimum. We apply our proposed flatness-constrained optimization to the existing FL techniques and obtain significant improvements, thereby establishing new state-of-the-art.
title Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2512.08314