Papers with Code 아카이브

Personalized Federated Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 7
보존된 평가 기록: 24

The federated learning setup presents numerous challenges including data heterogeneity (differences in data distribution), device heterogeneity (in terms of computation capabilities, network connection, etc.), and communication efficiency. Especially data heterogeneity makes it hard to learn a single shared global model that applies to all clients. To overcome these issues, Personalized Federated Learning (PFL) aims to personalize the global model for each client in the federation.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/google-research/federated/tree/master/personalization_benchmark

공식 코드

Motley: Benchmarking Heterogeneity and Personalization in Federated Learning

https://github.com/guobbin/PFL-MoE

공식 코드

PFL-MoE: Personalized Federated Learning Based on Mixture of Experts

https://github.com/guogangzhu/dualfed

공식 코드

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

https://github.com/heyuepeng/fedah

공식 코드

FedAH: Aggregated Head for Personalized Federated Learning

https://github.com/hongyouc/fed-rod

공식 코드

On Bridging Generic and Personalized Federated Learning for Image Classification

https://github.com/huangtiansheng/fedslr

공식 코드

Fusion of Global and Local Knowledge for Personalized Federated Learning

https://github.com/hukla/fedclassavg

공식 코드

FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks

https://github.com/icon-lab/pflsynth

공식 코드

One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesis

https://github.com/illidanlab/SplitMix

공식 코드

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

https://github.com/imguangyu/fedperfix

공식 코드

FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning

https://github.com/jianxu95/fedpac

공식 코드

Personalized Federated Learning with Feature Alignment and Classifier Collaboration

https://github.com/jimmyc96/spectral-dis-fl

공식 코드

Spectral Co-Distillation for Personalized Federated Learning

https://github.com/jonnyascott/pefll

공식 코드

PeFLL: Personalized Federated Learning by Learning to Learn

https://github.com/junyizhu-ai/confidence_aware_pfl

공식 코드

Confidence-aware Personalized Federated Learning via Variational Expectation Maximization

https://github.com/kelenlv/learn2pfed

공식 코드

Learn What You Need in Personalized Federated Learning

https://github.com/kxzxvbk/Fling

공식 코드

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

https://github.com/lancasterJie/FLAYER

공식 코드

Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning

https://github.com/lapisrocks/fedselect

공식 코드

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

https://github.com/liangh68/FedReMa

공식 코드

FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients

https://github.com/liehe/prfl

공식 코드

Provably Personalized and Robust Federated Learning

https://github.com/lipingyi/fedssa

공식 코드

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

https://github.com/litian96/ditto

공식 코드

Ditto: Fair and Robust Federated Learning Through Personalization

https://github.com/ljaiverson/pgfed

공식 코드

PGFed: Personalize Each Client's Global Objective for Federated Learning

https://github.com/lpd-epfl/attack_equivalence

공식 코드

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

https://github.com/microsoft/personalizedfl

공식 코드

Personalized Federated Learning with Adaptive Batchnorm for Healthcare

https://github.com/mmorafah/flis

공식 코드

FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution

https://github.com/nuaa-smartsensing/async-fl

공식 코드

FedModule: A Modular Federated Learning Framework

https://github.com/nvlabs/perada

공식 코드

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

https://github.com/omarfoq/fedem

공식 코드

Federated Multi-Task Learning under a Mixture of Distributions

https://github.com/omarfoq/knn-per

공식 코드

Personalized Federated Learning through Local Memorization

https://github.com/onizukalab/fedbench

공식 코드

An Empirical Study of Personalized Federated Learning

https://github.com/pechen123/2dbn_learning

공식 코드

Federated Learning of Dynamic Bayesian Network via Continuous Optimization from Time Series Data

https://github.com/pouyamghari/Fed-POE

공식 코드

Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning

https://github.com/pxqian/fedafa

공식 코드

Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation

https://github.com/regulation-sakak/cwFedAvg

공식 코드

Regularizing and Aggregating Clients with Class Distribution for Personalized Federated Learning

https://github.com/rong-dai/dispfl

공식 코드

DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.