Comprehensive and timely academic information on federated learning (papers, frameworks, datasets, tutorials, workshops)

37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 24 datasets. www.pfllib.com/

[ICLR'21] FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning, as well as corresponding mitigation strategies.

[ICLR 2021] HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients

AAAI 2023 accepted paper, FedALA: Adaptive Local Aggregation for Personalized Federated Learning

[NeurIPS 2023] "FedFed: Feature Distillation against Data Heterogeneity in Federated Learning"

The official code of KDD22 paper "FLDetecotor: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients"

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)

nips23-Dynamic Personalized Federated Learning with Adaptive Differential Privacy

Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

Robust aggregation for federated learning with the RFA algorithm.

Code for the CCS'22 paper "Federated Boosted Decision Trees with Differential Privacy"

This repository contains the official implementation for the manuscript: Make Landscape Flatter in Differentially Private Federated Learning (2023 CVPR)

A secure aggregation system for private federated learning

R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]

PyTorch implementation of Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance

The code of AAAI-21 paper titled "Defending against Backdoors in Federated Learning with Robust Learning Rate".

Federated learning via stochastic gradient descent

[Usenix Security 2024] Official code implementation of "BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning" (https://www.usenix.org/conference/usenixsecur…

The Code for "Federated Recommender with Additive Personalization"

Official code for "Federated Learning under Heterogeneous and Correlated Client Availability" (INFOCOM'23)

(CVPR 2024) Communication-Efficient Federated Learning with Accelerated Client Gradient

reproduce the FLTrust model based on the paper "FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping"

[ICLR2024] "Backdoor Federated Learning by Poisoning Backdoor-Critical Layers"

[CVPR2024] FedHCA^2: Towards Hetero-Client Federated Multi-Task Learning