Deep neural models, in recent years, have been successful in almost every field, even solving the most complex problem statements. However, these models are huge in size with millions (and even billions) of parameters, demanding heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of labeled data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called ‘Student-Teacher’ (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically used for vision tasks. In general, we investigate some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.

Mobile-edge Computing (MEC) has aroused significant attention for its performance to accelerate application's operation and enrich user's experience. With the increasing development of green computing, energy harvesting (EH) is considered as an available technology to capture energy from circumambient environment to supply extra energy for mobile devices. In this paper, we propose an online dynamic tasks assignment scheduling to investigate the tradeoff between energy consumption and execution delay for MEC system with EH capability. We formulate it into an average weighted sum of energy consumption and execution delay minimization problem of mobile device with the stability of buffer queues and battery level as constraints. Based on Lyapunov optimization method, we obtain the optimal scheduling about the CPU-cycle frequencies of mobile device and transmit power for data transmission. Besides, the dynamic online tasks offloading strategy is developed to modify the data backlogs of queues. The performance analysis shows the stability of the battery energy level and the tradeoff between energy consumption and execution delay. Moreover, the MEC system with EH devices and task buffers implements the high energy efficient and low latency communications. The performance of the proposed online algorithm is validated with extensive trace-driven simulations.

High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imaging using deep learning (DL). This study conducts a comprehensive and insightful survey and analysis of recent developments in deep HDR imaging methodologies. We hierarchically and structurally group existing deep HDR imaging methods into five categories based on (1) number/domain of input exposures, (2) number of learning tasks, (3) novel sensor data, (4) novel learning strategies, and (5) applications. Importantly, we provide a constructive discussion on each category regarding its potential and challenges. Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.

Mobile Edge Computing (MEC) brings abundant cloud resources to the edge of the network and provides great opportunities to improve user's quality of experience. While many recent studies have investigated the problem of computation offloading, service caching is also an important design topic of MEC. Service caching stores application-related databases or libraries in advance and enables corresponding user tasks to be offloaded. Due to the limited resources in the edge server, service caching decisions have to be made judiciously to maximize the system performance. In this paper, we study the problem of joint service caching, computation offloading, transmission and computing resource allocation in a general scenario of multiple users with multiple tasks. We aim to minimize the overall computation and delay costs for all users and formulate the optimization problem as a quadratically constrained quadratic program (QCQP) which is non-convex and NP-hard. To solve this challenging problem, we propose an efficiently approximate algorithm based on semidefinite relaxation (SDR) approach and alternating optimization which always computes a locally optimal solution. Moreover, we extend the study to the scenario where each user has a computation cost constraint. Simulation results show that our algorithm can minimize the system cost effectively by utilizing the available system resources.

Network robustness is critical for various industrial and social networks against malicious attacks, which has various meanings in different research contexts and here it refers to the ability of a network to sustain its functionality when a fraction of the network fail to work due to attacks. The rapid development of complex networks research indicates special interest and great concern about the network robustness, which is essential for further analyzing and optimizing network structures towards engineering applications. This comprehensive survey distills the important findings and developments of network robustness research, focusing on the a posteriori structural robustness measures for single-layer static networks. Specifically, the a posteriori robustness measures are reviewed from four perspectives: 1) network functionality, including connectivity, controllability and communication ability, as well as their extensions; 2) malicious attacks, including conventional and computation-based attack strategies; 3) robustness estimation methods using either analytical approximation or machine learning-based prediction; 4) network robustness optimization. Based on the existing measures, a practical threshold of network destruction is introduced, with the suggestion that network robustness should be measured only before reaching the threshold of destruction. Then, a posteriori and a priori measures are compared experimentally, revealing the advantages of the a posteriori measures. Finally, prospective research directions with respect to a posteriori robustness measures are recommended.