Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation

Excerpt

arXiv:2608.15660v1 Announce Type: cross Abstract: Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge. Federated knowledge distillation (FedKD) alleviates model heterogeneity by combining prototype-wise parameter aggregation and knowledge transfer across heterogeneous models. However, transmitting gradients still introduces considerable communication overh