Federated Learning of Shareable Bases for Personalization-Friendly Image Classification

04/16/2023
by   Hong-You Chen, et al.
6

Personalized federated learning (PFL) aims to harness the collective wisdom of clients' data to build customized models tailored to individual clients' data distributions. Existing works offer personalization primarily to clients who participate in the FL process, making it hard to encompass new clients who were absent or newly show up. In this paper, we propose FedBasis, a novel PFL framework to tackle such a deficiency. FedBasis learns a set of few, shareable “basis” models, which can be linearly combined to form personalized models for clients. Specifically for a new client, only a small set of combination coefficients, not the models, needs to be learned. This notion makes FedBasis more parameter-efficient, robust, and accurate compared to other competitive PFL baselines, especially in the low data regime, without increasing the inference cost. To demonstrate its applicability, we also present a more practical PFL testbed for image classification, featuring larger data discrepancies across clients in both the image and label spaces as well as more faithful training and test splits.

READ FULL TEXT
research
03/08/2021

Personalized Federated Learning using Hypernetworks

Personalized federated learning is tasked with training machine learning...
research
11/16/2021

Inference-Time Personalized Federated Learning

In Federated learning (FL), multiple clients collaborate to learn a mode...
research
06/08/2023

PeFLL: A Lifelong Learning Approach to Personalized Federated Learning

Personalized federated learning (pFL) has emerged as a popular approach ...
research
03/15/2023

Visual Prompt Based Personalized Federated Learning

As a popular paradigm of distributed learning, personalized federated le...
research
07/02/2021

On Bridging Generic and Personalized Federated Learning

Federated learning is promising for its ability to collaboratively train...
research
05/01/2023

Personalized Federated Learning under Mixture of Distributions

The recent trend towards Personalized Federated Learning (PFL) has garne...
research
02/13/2023

PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees

Personalized Federated Learning (pFL) has emerged as a promising solutio...

Please sign up or login with your details

Forgot password? Click here to reset