Secure Aggregation with Heterogeneous Quantization in Federated Learning

Understand

Secure model aggregation across many users is a key component of federated learning systems.

• The state-of-the-art protocols for secure model aggregation, which are based on additive masking, require all users to quantize their model updates to the same level of quantization.
• This severely degrades their performance due to lack of adaptation to available bandwidth at different users.
• We propose three schemes that allow secure model aggregation while using heterogeneous quantization.