paper-with-me

Papers

Flow: Per-instance Personalized Federated Learning

2023-09-21 · NeurIPS 2023 11

Federated learning (FL) suffers from data heterogeneity, where the diverse data distributions across clients make it challenging to train a single global model effectively. Existing personalization approaches aim to address the data heterogeneity issue by creating a personalized model for each client from the global model that fits their local data distribution. However, these personalized models may achieve lower accuracy than the global model in some clients, resulting in limited performance improvement compared to that without personalization. To overcome this limitation, we propose a per-instance personalization FL algorithm Flow. Flow creates dynamic personalized models that are adaptive not only to each client’s data distributions but also to each client’s data instances. The personalized model allows each instance to dynamically determine whether it prefers the local parameters or its global counterpart to make correct predictions, thereby improving clients’ accuracy. We provide theoretical analysis on the convergence of Flow and empirically demonstrate the superiority of Flow in improving clients’ accuracy compared to state-of-the-art personalization approaches on both vision and language-based tasks.

📄 PDF Abstract BibTeX

Code (1)

astuary/flow 공식 구현 pytorch

Similar Papers 제목 키워드 기반

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 LearningPersonalized Federated Learning

Trustworthy Personalized Bayesian Federated Learning via Posterior Fine-Tune

2024-02-25 · Mengen Luo, Chi Xu, Ercan Engin Kuruoglu

Performance degradation owing to data heterogeneity and low output interpretability are the most significant challenges faced by federated learning in practical applications. Personalized federated learning diverges from…

Federated LearningOut of Distribution (OOD) DetectionPersonalized Federated Learning

Client-supervised Federated Learning: Towards One-model-for-all Personalization

2024-03-28 · Peng Yan, Guodong Long

Personalized Federated Learning (PerFL) is a new machine learning paradigm that delivers personalized models for diverse clients under federated learning settings. Most PerFL methods require extra learning processes on a…

AllFederated LearningPersonalized Federated Learning

Towards Generalizable Personalized Federated Learning with Adaptive Local Adaptation

2021-09-29 · Sijia Chen, Baochun Li

Personalized federated learning aims to find a shared global model that can be adapted to meet personal needs on each individual device. Starting from such a shared initial model, devices should be able to easily adapt t…

Federated LearningMeta-LearningPersonalized Federated Learning

Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning

2025-08-27 · Tiandi Ye, Wenyan Liu, Kai Yao, Lichun Li 외 arxiv

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (…

Personalized Federated LearningVisual Prompt Tuning