AI RESEARCH
Representation-Aligned Multi-Scale Personalization for Federated Learning
arXiv CS.LG
•
ArXi:2604.11278v1 Announce Type: new 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.