Labeling data (e.g., labeling the people, objects, actions and scene in images) comprehensively and efficiently is a widely needed but challenging task. Numerous models were proposed to label various data and many approaches were designed to enhance the ability of deep learning models or accelerate them. Unfortunately, a single machine-learning model is not powerful enough to extract various semantic information from data. Given certain applications, such as image retrieval platforms and photo album management apps, it is often required to execute a collection of models to obtain sufficient labels. With limited computing resources and stringent delay, given a data stream and a collection of applicable resource-hungry deep-learning models, we design a novel approach to adaptively schedule a subset of these models to execute on each data item, aiming to maximize the value of the model output (e.g., the number of high-confidence labels). Achieving this lofty goal is nontrivial since a model's output on any data item is content-dependent and unknown until we execute it. To tackle this, we propose an Adaptive Model Scheduling framework, consisting of 1) a deep reinforcement learning-based approach to predict the value of unexecuted models by mining semantic relationship among diverse models, and 2) two heuristic algorithms to adaptively schedule the model execution order under a deadline or deadline-memory constraints respectively. The proposed framework doesn't require any prior knowledge of the data, which works as a powerful complement to existing model optimization technologies. We conduct extensive evaluations on five diverse image datasets and 30 popular image labeling models to demonstrate the effectiveness of our design: our design could save around 53\% execution time without loss of any valuable labels.
Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling
Northeast Electric Power University（东北电力大学）；State Grid Zibo Power Supply Company（国网淄博供电公司）；State Grid Beijing Electric Power Company（国网北京市电力公司）；State Grid Jining Power Supply Company（国网济宁供电公司）
Hybrid intelligence for dynamic job-shop scheduling with deep reinforcement learning and attention mechanism
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Intelligent Systems Science and Engineering, Jinan University（暨南大学智能系统科学与工程学院）
Optimal scheduling of island integrated energy systems considering multi-uncertainties and hydrothermal simultaneous transmission: A deep reinforcement learning approach
Northeast Electric Power University（东北电力大学）；Huazhong University of Science and Technology（华中科技大学）；Cranfield University（克兰菲尔德大学）
A Methodological Framework for Measuring Spatial Labeling Similarity
School of Statistics and Mathematics, Zhongnan University of Economics and Law（中南财经政法大学统计与数学学院）；Department of Biomedical Engineering, Southern University of Science and Technology（南方科技大学生物医学工程系）；School of Information Engineering, Zhongnan University of Economics and Law（中南财经政法大学信息工程学院）；School of Life Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of science（中国科学院大学杭州高等研究院生命科学学院）
DPBalance: Efficient and Fair Privacy Budget Scheduling for Federated Learning as a Service
UM-SJTU Joint Institute, Shanghai Jiao Tong University（上海交通大学密西根学院）；Cooperative Medianet Innovation Center (CMIC), Shanghai Jiao Tong University（上海交通大学合作媒体创新中心）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）
