Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning

Excerpt

arXiv:2609.39646v1 Announce Type: new Abstract: Federated learning faces severe communication bottlenecks when clients upload high-dimensional model updates. Existing methods often compress these updates uniformly across all layers. This uniform approach ignores the heterogeneous value of different parameter blocks and wastes limited bandwidth on insensitive layers. To address this issue, we propose Layer-wise Budgeted Adaptive Transmission (LBAT). LBAT reframes federated communication under ext