Given the fast growth of intelligent devices, it is expected that a large number of high-stakes artificial intelligence (AI) applications, e. g., drones, autonomous cars, and tac?tile robots, will be deployed at the e...Given the fast growth of intelligent devices, it is expected that a large number of high-stakes artificial intelligence (AI) applications, e. g., drones, autonomous cars, and tac?tile robots, will be deployed at the edge of wireless networks in the near future. Therefore, the intelligent communication networks will be designed to leverage advanced wireless tech?niques and edge computing technologies to support AI-enabled applications at various end devices with limited communication, computation, hardware and energy resources. In this article, we present the principles of efficient deployment of model inference at network edge to provide low-latency and energy-efficient AI services. This includes the wireless distribut?ed computing framework for low-latency device distributed model inference as well as the wireless cooperative transmission strategy for energy-efficient edge cooperative model infer?ence. The communication efficiency of edge inference systems is further improved by build?ing up a smart radio propagation environment via intelligent reflecting surface.展开更多
By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the earl...By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the early exits introduce additional computation overhead,which is unfavorable for resource-constrained edge artificial intelligence(AI).In this paper,we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.Specifically,we design a low-complexity module,namely the exit predictor,to guide some distinctly“hard”samples to bypass the computation of the early exits.Besides,considering the varying communication bandwidth,we extend the early exit prediction mechanism for latency-aware edge inference,which adapts the prediction thresholds of the exit predictor and the confidence thresholds of the early-exit network via a few simple regression models.Extensive experiment results demonstrate the effectiveness of the exit predictor in achieving a better tradeoff between accuracy and on-device computation overhead for early-exit networks.Besides,compared with the baseline methods,the proposed method for latency-aware edge inference attains higher inference accuracy under different bandwidth conditions.展开更多
文摘Given the fast growth of intelligent devices, it is expected that a large number of high-stakes artificial intelligence (AI) applications, e. g., drones, autonomous cars, and tac?tile robots, will be deployed at the edge of wireless networks in the near future. Therefore, the intelligent communication networks will be designed to leverage advanced wireless tech?niques and edge computing technologies to support AI-enabled applications at various end devices with limited communication, computation, hardware and energy resources. In this article, we present the principles of efficient deployment of model inference at network edge to provide low-latency and energy-efficient AI services. This includes the wireless distribut?ed computing framework for low-latency device distributed model inference as well as the wireless cooperative transmission strategy for energy-efficient edge cooperative model infer?ence. The communication efficiency of edge inference systems is further improved by build?ing up a smart radio propagation environment via intelligent reflecting surface.
基金fund of the Hong Kong Polytechnic University(P0038174)。
文摘By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the early exits introduce additional computation overhead,which is unfavorable for resource-constrained edge artificial intelligence(AI).In this paper,we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.Specifically,we design a low-complexity module,namely the exit predictor,to guide some distinctly“hard”samples to bypass the computation of the early exits.Besides,considering the varying communication bandwidth,we extend the early exit prediction mechanism for latency-aware edge inference,which adapts the prediction thresholds of the exit predictor and the confidence thresholds of the early-exit network via a few simple regression models.Extensive experiment results demonstrate the effectiveness of the exit predictor in achieving a better tradeoff between accuracy and on-device computation overhead for early-exit networks.Besides,compared with the baseline methods,the proposed method for latency-aware edge inference attains higher inference accuracy under different bandwidth conditions.