3 papers
cs.DC2026
Quota-Based Aging for Prediction-Guided Scheduling in LLM Serving
Hanzhi Zhang, Anxuan Che, Hang Qi +2
Large language model (LLM) serving systems use token-level continuous batching to improve resource utilization, but heterogeneous response lengths complicate request scheduling. Pr…
cs.LG2025
Cluster-Based Client Selection for Dependent Multi-Task Federated Learning in Edge Computing
Jieping Luo, Qiyue Li, Zhizhang Liu +3
We study the client selection problem in Federated Learning (FL) within mobile edge computing (MEC) environments, particularly under the dependent multi-task settings, to reduce th…
cs.LG2025
Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
Qiyue Li, Yingxin Liu, Hang Qi +3
We consider the client selection problem in wireless Federated Learning (FL), with the objective of reducing the total required time to achieve a certain level of learning accuracy…