Bringing AI To Edge: From Deep Learning's Perspective
HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University（南洋理工大学惠普-南大数字制造企业实验室）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；Innovations and Experiences–Business Personal Systems, HP Inc.（惠普公司创新与体验-个人系统业务部）
Di Liu, Hao Kong, Xiangzhong Luo, Weichen Liu, Ravi Subramaniam
Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods which are applicable to edge systems are proposed intensively, a holistic review would enable edge computing engineers and community to know the state-of-the-art deep learning techniques which are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions.
A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas
Technical University of Munich, Germany（慕尼黑技术大学）；TUM School of Computation, Information and Technology（慕尼黑技术大学计算、信息与技术学院）；Department of Informatics（信息学院）
PRISM: Distributed Inference for Foundation Models at Edge
Department of Electrical and Computer Engineering, Aarhus University（电子与计算机工程系，奥胡斯大学）；Faculty of Information Technology and Communication Sciences, Tampere University（信息科技与通信科学学院，塔尔库大学）
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
Harvard University（哈佛大学）
事后可解释性领域的一个关键问题是方法之间缺乏共同的基本目标。例如，一些方法的动机是函数逼近，一些是博弈论概念，还有一些是获得清晰的可视化。这种目标的碎片化不仅导致对解释的概念理解不一致，而且还导致不知道何时使用哪种方法的实际挑战。在这项工作中，我们开始通过统一八种流行的事后解释方法（LIME，C-LIME，KernelSHAP，Occlusion，Vanilla Quantients，Quantients x Input，SmoothGrad和Integrated Quantients）来解决这些挑战。我们发现，这些方法都执行本地功能近似的黑盒模型，不同的只是在附近和损失函数用于执行近似。这种统一使我们能够（1）陈述解释方法的没有免费的午餐定理，证明没有任何方法可以在所有邻域中表现最佳，以及（2）提供基于对黑盒模型的忠诚度的方法选择的指导原则。我们使用各种真实世界的数据集，模型类和预测任务来实证验证这些理论结果。通过将不同的解释方法纳入一个共同的框架，这项工作（1）推进了对这些方法的概念理解，揭示了它们共享的局部函数逼近目标、属性和彼此之间的关系，（2）指导这些方法在实践中的使用，提供了一个原则性的方法来选择方法并为创建新方法铺平道路。
