Federated Learning of Shareable Bases for Personalization-Friendly Image Classification

2023-04-16 · Hong-You Chen, Jike Zhong, Mingda Zhang, Xuhui Jia, Hang Qi, Boqing Gong, Wei-Lun Chao, Li Zhang

Personalized federated learning (PFL) aims to harness the collective wisdom of clients' data while building personalized 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 model weights, needs to be learned. This notion makes FedBasis more parameter-efficient, robust, and accurate than competitive PFL baselines, especially in the low data regime, without increasing the inference cost. To demonstrate the effectiveness and applicability of FedBasis, 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.

📄 PDF Abstract BibTeX arXiv:2304.07882

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning image-classification Image Classification Personalized Federated Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음

More Industry-friendly: Federated Learning with High Efficient Design

2020-12-16 · Dingwei Li, Qinglong Chang, Lixue Pang, Yanfang Zhang 외

Although many achievements have been made since Google threw out the paradigm of federated learning (FL), there still exists much room for researchers to optimize its efficiency. In this paper, we propose a high efficien…

Federated Learning Vocal Bursts Intensity Prediction

DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations

2024-07-25 · Guogang Zhu, Xuefeng Liu, Jianwei Niu, Shaojie Tang 외

In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, ex…

Federated Learning Personalized Federated Learning

Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization

2026-04-24 · Hefeng Zhou, Xuan Liu, Sicheng Chen, Wutong Zhang 외 arxiv

Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modalities. Under such heterogeneity, a single global model is often insuffi…

Cross-Modal Retrieval

Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing

2022-11-28 · Kunjal Panchal, Sunav Choudhary, Nisarg Parikh, Lijun Zhang 외

Personalization in Federated Learning (FL) aims to modify a collaboratively trained global model according to each client. Current approaches to personalization in FL are at a coarse granularity, i.e. all the input insta…

Federated Learning Personalized Federated Learning

FedBABU: Towards Enhanced Representation for Federated Image Classification

2021-06-04 · Jaehoon Oh, Sangmook Kim, Se-Young Yun

Federated learning has evolved to improve a single global model under data heterogeneity (as a curse) or to develop multiple personalized models using data heterogeneity (as a blessing). However, little research has cons…

Classification Federated Learning image-classification Image Classification