2 papers
cs.LG2025
Kuramoto-FedAvg: Using Synchronization Dynamics to Improve Federated Learning Optimization under Statistical Heterogeneity
Aggrey Muhebwa, Khotso Selialia, Fatima Anwar +1
Federated learning on heterogeneous (non-IID) client data experiences slow convergence due to client drift. To address this challenge, we propose Kuramoto-FedAvg, a federated optim…
cs.CL2025
Causal Distillation: Transferring Structured Explanations from Large to Compact Language Models
Aggrey Muhebwa, Khalid K. Osman
Large proprietary language models exhibit strong causal reasoning abilities that smaller open-source models struggle to replicate. We introduce a novel framework for distilling cau…