Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning

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 extreme uplink budgets as a resource allocation problem. Our framework dynamically estimates the transmission value of different layers utilising local training signals. It then employs an exact byte dynamic programming allocator to determine optimal rank and bit configurations under strict budgets. We validate LBAT on highly heterogeneous federated tabular prediction and data generation tasks. Extensive experiments demonstrate that LBAT consistently outperforms uniform rank, uniform quantisation, and fixed compression baselines across various extreme budget regimes. Furthermore, it achieves significantly better communication and utility tradeoffs while preserving essential distributional fidelity.

Related

• FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection
• Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning
• Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data
• Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation

Source: arXiv cs.LG | 2026-10-01