IEEE

Communication-Efficient Federated Learning via Dynamic Sparsity: An Adaptive Pruning Ratio Based on Weight Importance

Abstract: In Federated Learning (FL), optimizing communication efficiency and utilizing computational resources present key challenges. This paper proposes the Federated Adaptive Deep Sparse ...
Security Boulevard

AI-Driven Anomaly Detection in Post-Quantum Context Streams

Discover how AI-driven anomaly detection safeguards post-quantum context streams in Model Context Protocol (MCP) environments, ensuring robust security for AI infrastructure against future threats.
IEEE

Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets

Abstract: In a real federated learning (FL) system, communication overhead for passing model parameters between the clients and the parameter server (PS) is often a bottleneck. Hierarchical federated ...
The Nation Newspaper

Ogweda awarded as 277th certified global tech hero

Haruna Ogweda has been immortalised as the 277th Certified Global Tech Hero, a recognition that celebrates a career defined ...