Representation-Aligned Multi-Scale Personalization for Federated Learning

TL;DR

FRAMP introduces a flexible federated learning framework that generates personalized, resource-aware models for clients, improving adaptation and generalization across diverse settings.

Contribution

It proposes a unified approach to create client-specific models from compact descriptors, enhancing personalization and resource adaptation in federated learning.

Findings

FRAMP improves model generalization across vision and graph benchmarks.

Clients trained with FRAMP achieve better adaptation to resource constraints.

The framework maintains global semantic consistency among personalized models.

Abstract

In federated learning (FL), accommodating clients with diverse resource constraints remains a significant challenge. A widely adopted approach is to use a shared full-size model, from which each client extracts a submodel aligned with its computational budget. However, regardless of the specific scoring strategy, these methods rely on the same global backbone, limiting both structural diversity and representational adaptation across clients. This paper presents FRAMP, a unified framework for personalized and resource-adaptive federated learning. Instead of relying on a fixed global model, FRAMP generates client-specific models from compact client descriptors, enabling fine-grained adaptation to both data characteristics and computational budgets. Each client trains a tailored lightweight submodel and aligns its learned representation with others to maintain global semantic consistency. Extensive experiments on vision and graph benchmarks demonstrate that FRAMP enhances generalization and adaptivity across a wide range of client settings.