DQRE-SCnet: A novel hybrid approach for selecting users in Federated Learning with Deep-Q-Reinforcement Learning based on Spectral Clustering

no code implementations • 7 Nov 2021 • Mohsen Ahmadi, Ali Taghavirashidizadeh, Danial Javaheri, Armin Masoumian, Saeid Jafarzadeh Ghoushchi, Yaghoub Pourasad

In many applications, learning participant communication rounds benefit from collecting their own private data sets, teaching detailed machine learning models on the real data, and sharing the benefits of using these models.

BIG-bench Machine Learning Federated Learning