Adaptive Model Scheduling for Resource-efficient Data Labeling

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 does not 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.

The Control System in the Hotel and Restaurant Business: Conceptual Approach

The topicality. In today’s crisis of hotel and restaurant business in terms of ensuring the effectiveness of the management component is relevant to the use of controlling as an element of crisis management in the hospitality industry, which allows you to take management to a qualitatively new level by evaluating, coordinating, coordinating, optimizing and monitoring all services. and divisions operating at the enterprise. The purpose of the article is to develop and substantiate the conceptual theoretical and methodological provisions and practical recommendations for improving the controlling system in the hotel and restaurant business. Research methods. In forming the methodology of conceptual vision of the controlling system in the hotel and restaurant business and the main directions of its application used a set of general and special research methods: methods of observation, modeling, analysis and synthesis, comparison, strategic analysis, abstract modeling and historical logic. Results. The key features of improving the controlling system at the hotel and restaurant business have been identified and substantiated. The stages of its creation are analyzed, in particular the stage of preparation, implementation and automation. The main conceptual principles of improving the controlling system in the field of hospitality are outlined. A conceptual adaptive model of improving the controlling system in the hotel and restaurant business has been designed and substantiated, which is characterized by complexity and cyclicity and consists of three circles (internal, middle and external), for each of which the parameters of flow and interconnection are defined. Conclusions and discussions. The scientific novelty of the obtained results lies in the design and substantiation of a conceptual adaptive model of controlling system improvement at hotel and restaurant business enterprises, which has a cyclical nature and allows to provide continuous and continuous improvement of both the controlling system and the enterprise as a whole. The practical significance of the obtained results is manifested in the possibility of applying the developed and substantiated theoretical and methodological and applied conceptual aspects in the real business practice of hotel and restaurant business enterprises in order to ensure their efficiency and competitiveness in the services market of Ukraine and abroad.

An Adaptive Model of Demand Adjustment in Weighted Majority Games

This paper presents a simple adaptive model of demand adjustment in cooperative games and analyzes this model in weighted majority games. In the model, a randomly chosen player sets her demand to the highest possible value subject to the demands of other coalition members being satisfied. This basic process converges to the aspiration set. By introducing some perturbations into the process, we show that the set of separating aspirations, i.e., demand vectors in which no player is indispensable in order for other players to achieve their demands, is the one most resistant to mutations. We then apply the process to weighted majority games. We show that in symmetric majority games and in apex games, the unique separating aspiration is the unique stochastically stable one.