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/Ambient-AI/FedSIM

공식 코드

Personalized Federated Learning with Server-Side Information

https://github.com/AvivSham/pFedHN

공식 코드

Personalized Federated Learning using Hypernetworks

https://github.com/CambridgeCIA/FedMAP

공식 코드

FedMAP: Unlocking Potential in Personalized Federated Learning through Bi-Level MAP Optimization

https://github.com/CharlieDinh/pFedMe

공식 코드

Personalized Federated Learning with Moreau Envelopes

https://github.com/IdanAchituve/pFedGP

공식 코드

Personalized Federated Learning with Gaussian Processes

https://github.com/MLOPTPSU/FedTorch

공식 코드

Adaptive Personalized Federated Learning

https://github.com/MMorafah/Sub-FedAvg

공식 코드

Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity

https://github.com/NVlabs/FedFomo

공식 코드

Personalized Federated Learning with First Order Model Optimization

https://github.com/RenpuLiu/flute

공식 코드

Federated Representation Learning in the Under-Parameterized Regime

https://github.com/Sherrylife/FedDWA

공식 코드

FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment

https://github.com/TsingZ0/FedALA

공식 코드

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

https://github.com/TsingZ0/GPFL

공식 코드

GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning

https://github.com/TsingZ0/HtFL

공식 코드

PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark

https://github.com/TsingZ0/PFLlib

공식 코드

PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark

https://github.com/XiaoyanWork/DAMe

공식 코드

DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism

https://github.com/albietz/ppsgd

공식 코드

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning

https://github.com/alibaba/federatedscope

공식 코드

pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning

https://github.com/annavettoruzzo/cafeme

공식 코드

Personalized Federated Learning with Contextual Modulation and Meta-Learning

https://github.com/arvintashakori/SemiPFL

공식 코드

SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence

https://github.com/astuary/flow

공식 코드

Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing

https://github.com/axedge1983/li

공식 코드

Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server

https://github.com/baowenxuan/atp

공식 코드

Adaptive Test-Time Personalization for Federated Learning

https://github.com/bapfl/code

공식 코드

You Can Backdoor Personalized Federated Learning

https://github.com/bbbbbbzhou/fedftn

공식 코드

FedFTN: Personalized Federated Learning with Deep Feature Transformation Network for Multi-institutional Low-count PET Denoising

https://github.com/bokun-wang/moml

공식 코드

Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning

https://github.com/boxinz17/PFL-Unified-Framework

공식 코드

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

https://github.com/cj-mclaughlin/pfedfda

공식 코드

Personalized Federated Learning via Feature Distribution Adaptation

https://github.com/dannis97500/pm-moe

공식 코드

PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning

https://github.com/dawenzi098/SFL-Structural-Federated-Learning

공식 코드

Personalized Federated Learning With Graph

https://github.com/dual-grp/fedu_fmtl

공식 코드

A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularization

https://github.com/emiliocantuc/personalized-fl-via-stacking

공식 코드

Personalized Federated Learning via Stacking

https://github.com/ericloong/da-dpfl

공식 코드

Decentralized Personalized Federated Learning based on a Conditional Sparse-to-Sparser Scheme

https://github.com/ericssonresearch/fl-moe

공식 코드

Adaptive Expert Models for Personalization in Federated Learning

https://github.com/g2lab/pcfbl

공식 코드

Privacy-preserving patient clustering for personalized federated learning

https://github.com/getalp/FedAli

공식 코드

FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal Transport

https://github.com/google-research/federated

공식 코드

Motley: Benchmarking Heterogeneity and Personalization in Federated Learning

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