FedCollab

Collaboration optimizer

An algorithm that optimizes collaboration in federated learning by clustering clients into non-overlapping coalitions based on data quantity and pairwise distribution distances.

[ICML 2023] Optimizing the Collaboration Structure in Cross-Silo Federated Learning. Wenxuan Bao, Haohan Wang, Jun Wu, Jingrui He.

GitHub

16 stars
3 watching
2 forks
Language: Python
last commit: about 3 years ago
clustered-federated-learningfederated-learningpersonalized-federated-learning

Related projects:

RepositoryDescriptionStars
litian96/fedproxAn optimization framework designed to address heterogeneity in federated learning across distributed networks655
mingruiliu-ml-lab/episodeAn algorithm for Federated Learning with heterogeneous data, designed to optimize deep neural networks and improve performance2
optimization-ai/icml2023_fedxlAn implementation of a federated learning algorithm for optimization problems with compositional pairwise risk optimization.2
zackzikaixiao/fedgrabA tool for training federated learning models with adaptive gradient balancing to handle class imbalance in multi-client scenarios.14
cuis15/learning-to-collaborateA research project focused on developing methods for learning to collaborate in multi-objective optimization problems using machine learning and deep learning techniques.11
divyansh03/fedexpAn implementation of a federated averaging algorithm with an extrapolation approach to speed up distributed machine learning training on client-held data.9
illidanlab/splitmixAn algorithm for distributed learning with flexible model customization during training and testing40
dos-group/fedzeroAn implementation of federated learning optimized for training on renewable energy sources and spare compute capacity to minimize carbon emissions.19
hui-po-wang/progfedAn approach to efficient federated learning by progressively training models on client devices with reduced communication and computation requirements.20
sungwon-han/fedxAn unsupervised federated learning algorithm that uses cross knowledge distillation to learn meaningful data representations from local and global levels.69
zhenqincn/fedapenAn implementation of cross-silo federated learning with adaptability to statistical heterogeneity12
clreda/near-optimal-federatedAn open-source software project implementing collaborative learning in bandits to achieve near-optimal results1
xidongwu/federated-minimax-and-conditional-stochastic-optimizationThis project presents optimization techniques for federated learning and minimax games in the context of machine learning1
mc-nya/fednestAn implementation of a federated optimization algorithm for distributed machine learning6
hongliny/fco-icml21This code repository provides an implementation of Federated Composite Optimization for decentralized machine learning12