J. Tang

HERL: Tiered Federated Learning with Adaptive Homomorphic Encryption using Reinforcement Learning

2024 · arXiv (Cornell University)

Federated Learning is a well-researched approach for collaboratively training machine learning models across decentralized data while preserving privacy. However, integrating Homomorphic Encryption to ensure data confidentiality introduces significant computational and communication overheads, particularly in heterogeneous …