4 papers · 1 filter
Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization
Zheng Lin, Shaoke Fang, Yuxin Zhang +6
While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive memory requirements. Extract…
Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW
Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi +2
Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constr…
FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selection
Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi +3
Reliable access selection in dynamic and heterogeneous indoor-outdoor environments is challenging because instantaneous radio measurements alone cannot capture future QoS degradati…
GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems
Zheng Lin, Ons Aouedi, Zihan Fang +4
The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge devices. Parallel split learning (P…