HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
This work introduces Homomorphic Encryption-Aware Training (HEAT), a fine-tuning method that makes the per-nonlinearity iteration counts learnable, enabling them and the model weights to co-adapt during training.
Alessandro Zirilli, Davide Marincione, E. Kornaropoulos et al.
· 0 citations