AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

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

Jianqing Zhang, Yang Liu, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Jian Cao

JMLR 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Personalization with global-local trade-off · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use personalized FL (FedCP) instead of FedAvgFedAvg · Pathological label skew Cifar100test accuracy (%): 25.98 -> 71.80Improved
use FedDBE instead of FedAvgFedAvg · Practical label skew Cifar100test accuracy (%): 31.89 -> 64.39Improved
use GPFL instead of FedAvgFedAvg · Practical label skew AG Newstest accuracy (%): 87.12 -> 97.97Improved
use FedProx instead of FedAvgFedAvg · Pathological label skew FMNISTtest accuracy (%): 80.41 -> 78.08Hurt
use FedGen instead of FedAvgFedAvg · Pathological label skew Cifar100test accuracy (%): 25.98 -> 20.80Hurt
use FedProx instead of FedAvgFedAvg · Practical label skew Cifar100test accuracy (%): 31.89 -> 31.99No clear effect
use ResNet-18 instead of 4-layer CNN for FedAvgFedAvg · Practical label skew Tiny-ImageNettest accuracy (%): 19.46 -> 19.45No clear effect
use ResNet-18 instead of 4-layer CNN for FedCPFedCP · Practical label skew Tiny-ImageNettest accuracy (%): 43.49 -> 44.18No clear effect
use ResNet-18 instead of 4-layer CNN for pFedMepFedMe · Practical label skew Tiny-ImageNettest accuracy (%): 26.93 -> 33.44Improved
use FedALA instead of Per-FedAvg (meta-learning)Per-FedAvg · Practical label skew Cifar100test accuracy (%): 44.28 -> 55.92Improved
use FedBABU instead of FedAvgFedAvg · Practical label skew AG Newstest accuracy (%): 87.12 -> 95.86Improved
use FedAMP instead of FedAvgFedAvg · Practical label skew AG Newstest accuracy (%): 87.12 -> 83.35Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy