paper-with-me

Papers

Federated Learning with Personalization Layers

2019-12-02 · Manoj Ghuhan Arivazhagan, Vinay Aggarwal, Aaditya Kumar Singh, Sunav Choudhary

The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence, improving data privacy. This sharply deviates from traditional machine learning and necessitates the design of algorithms robust to various sources of heterogeneity. Specifically, statistical heterogeneity of data across user devices can severely degrade the performance of standard federated averaging for traditional machine learning applications like personalization with deep learning. This paper pro-posesFedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, which can combat the ill-effects of statistical heterogeneity. We demonstrate effectiveness ofFedPerfor non-identical data partitions ofCIFARdatasetsand on a personalized image aesthetics dataset from Flickr.

📄 PDF Abstract BibTeX arXiv:1912.00818

Code (4)

KarhouTam/FL-bench pytorch
TsingZ0/FL-IoT pytorch
TsingZ0/PFL-Non-IID pytorch
adap/flower tf

Tasks

BIG-bench Machine LearningFederated Learning

Similar Papers 제목 키워드 기반

Federated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients

2023-09-22 · Shourya Bose, Kibaek Kim

The advent of smart meters has enabled pervasive collection of energy consumption data for training short-term load forecasting (STLF) models. In response to privacy concerns, federated learning (FL) has been proposed as…

Federated LearningLoad ForecastingPrivacy Preserving

Addressing Heterogeneity in Federated Load Forecasting with Personalization Layers

2024-04-01 · Shourya Bose, Yu Zhang, Kibaek Kim

The advent of smart meters has enabled pervasive collection of energy consumption data for training short-term load forecasting models. In response to privacy concerns, federated learning (FL) has been proposed as a priv…

Federated LearningLoad ForecastingPrivacy Preserving

pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup

2025-01-19 · Yasaman Saadati, Mohammad Rostami, M. Hadi Amini

Traditional Federated Learning (FL) methods encounter significant challenges when dealing with heterogeneous data and providing personalized solutions for non-IID scenarios. Personalized Federated Learning (PFL) approach…

Federated LearningPersonalized Federated Learning

pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learning

2026-06-15 · Zhuodong Liu, Xiangyu Li, Zhihao Zhang arxiv

Federated unlearning (FU) enables the removal of specific data contributions from federated learning (FL) models to comply with regulations such as the General Data Protection Regulation (GDPR). However, most existing FU…

Personalized Federated Learning

UA-PDFL: A Personalized Approach for Decentralized Federated Learning

2024-12-16 · Hangyu Zhu, Yuxiang Fan, Zhenping Xie

Federated learning (FL) is a privacy preserving machine learning paradigm designed to collaboratively learn a global model without data leakage. Specifically, in a typical FL system, the central server solely functions a…

Federated LearningPrivacy Preserving