Research
MUC-FL: Block-Wise Marginal Utility Contribution for Communication-Efficient Federated Learning
arXiv:2609.10545v1 Announce Type: cross Abstract: Federated Learning (FL) enables distributed model training without centralizing data but suffers from high communication overhead. To address this, we
arXiv:2609.10545v1 Announce Type: cross Abstract: Federated Learning (FL) enables distributed model training without centralizing data but suffers from high communication overhead. To address this, we propose Block-Wise Marginal Utility Contribution (MUC), a framework that selectively transmits only the most impactful data blocks based on their contribution to model performance. To evaluate our framework, we apply it to a multimodal dataset integrated from multiple MIMIC clinical datasets and show that only 24 out of 1,135 candidate blocks (1.76%) carry meaningful improvement signals, enabling a potential communication reduction of 45-50% while maintaining or improving model quality. Our deduplication-based block selection achieves a macro F1 score of 0.8566 compared to 0.8155 for standard federated optimization, demonstrating that selective transmission can improve performance, particularly in underrepresented classes.
Related
- DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
- Joint Model and Data Sparsification via the Marginal Likelihood
- Subspace Optimization for Efficient Federated Learning under Heterogeneous Data
Source: arXiv cs.LG | 2026-09-11