Code for the paper Personalized Federated Learning with Contextual Modulation and Meta-Learning accepted at SIAM Conference on Data Mining (2024). https://arxiv.org/abs/2312.15191
In this paper we propose CAFeMe, a context-aware federated learning solution that leverages meta-learning to facilitate personalization to each client.
- RMNIST with shards and Dirichlet partition
- CIFAR-10 with shards and Dirichlet partition
- FEMNIST
- Meta-Dataset
To run the code, use the main.py file. The hyperparameters used for obtaining the results in the paper are provided in the arguments.py file.