4 papers
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…
Adaptive Client Clustering and Coordination for Federated Learning Workflow Management in Edge Networks
Jieping Luo, Qiyue Li, Yuxuan Chen +4
Federated learning (FL) is increasingly deployed as a managed learning service rather than as a set of isolated training jobs. In networked edge environments, dependent FL service…
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…
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…