Tong Liu

TL;DR: In this paper, an attention-based double deep $Q$ network (DDQN) is proposed to estimate the cumulative latency and energy rewards achieved by each action, and a context-aware attention mechanism is designed to adaptively assign different weights to the values of each action.

TL;DR: Wang et al. as discussed by the authors proposed a privacy-oriented task offloading method that can resist attacks from privacy attackers with prior knowledge, where the local computing model, channel model, and privacy loss model are defined and used to quantify evaluation indicators, such those related to privacy, time, and energy.

TL;DR: A novel Graph-based Spatial Dependency modeling (GSD) module, which focuses on explicitly modeling complex geographical influences by leveraging graph embedding, and a novelgraph-enhanced Spatial-Temporal network (GSTN), which incorporates user spatial and temporal dependencies for next POI recommendation.

TL;DR: An active learning scheme is proposed, which iteratively selects valuable locations to collect sensing data and provides incentives to the participants, and air pollution concentrations in unselected locations are inferred via CS.