skip to main content

Title: Automating Deep Neural Network Model Selection for Edge Inference
The ever increasing size of deep neural network (DNN) models once implied that they were only limited to cloud data centers for runtime inference. Nonetheless, the recent plethora of DNN model compression techniques have successfully overcome this limit, turning into a reality that DNN-based inference can be run on numerous resource-constrained edge devices including mobile phones, drones, robots, medical devices, wearables, Internet of Things devices, among many others. Naturally, edge devices are highly heterogeneous in terms of hardware specification and usage scenarios. On the other hand, compressed DNN models are so diverse that they exhibit different tradeoffs in a multi-dimension space, and not a single model can achieve optimality in terms of all important metrics such as accuracy, latency and energy consumption. Consequently, how to automatically select a compressed DNN model for an edge device to run inference with optimal quality of experience (QoE) arises as a new challenge. The state-of-the-art approaches either choose a common model for all/most devices, which is optimal for a small fraction of edge devices at best, or apply device-specific DNN model compression, which is not scalable. In this paper, by leveraging the predictive power of machine learning and keeping end users in the loop, more » we envision an automated device-level DNN model selection engine for QoE-optimal edge inference. To concretize our vision, we formulate the DNN model selection problem into a contextual multi-armed bandit framework, where features of edge devices and DNN models are contexts and pre-trained DNN models are arms selected online based on the history of actions and users' QoE feedback. We develop an efficient online learning algorithm to balance exploration and exploitation. Our preliminary simulation results validate our algorithm and highlight the potential of machine learning for automating DNN model selection to achieve QoE-optimal edge inference. « less
Authors:
; ; ;
Award ID(s):
1910208 1551661 1610471
Publication Date:
NSF-PAR ID:
10195209
Journal Name:
IEEE First International Conference on Cognitive Machine Intelligence (CogMI)
Page Range or eLocation-ID:
184 to 193
Sponsoring Org:
National Science Foundation
More Like this
  1. With the emergence of more and more powerful chipsets and hardware and the rise of Artificial Intelligence of Things (AIoT), there is a growing trend for bringing Deep Neural Network (DNN) models to empower mobile and edge devices with intelligence such that they can support attractive AI applications on the edge in a real-time or near real-time manner. To leverage heterogeneous computational resources (such as CPU, GPU, DSP, etc) to effectively and efficiently support concurrent inference of multiple DNN models on a mobile or edge device, we propose a novel online Co-Scheduling framework based on deep REinforcement Learning (DRL), whichmore »we call COSREL. COSREL has the following desirable features: 1) it achieves significant speedup over commonly-used methods by efficiently utilizing all the computational resources on heterogeneous hardware; 2) it leverages emerging Deep Reinforcement Learning (DRL) to make dynamic and wise online scheduling decisions based on system runtime state; 3) it is capable of making a good tradeoff among inference latency, throughput and energy efficiency; and 4) it makes no changes to given DNN models, thus preserves their accuracies. To validate and evaluate COSREL, we conduct extensive experiments on an off-the-shelf Android smartphone with widely-used DNN models to compare it with three commonly-used baselines. Our experimental results show that 1) COSREL consistently and significantly outperforms all the baselines in terms of both throughput and latency; and 2) COSREL is generally superior to all the baselines in terms of energy efficiency.« less
  2. AI applications powered by deep learning inference are increasingly run natively on edge devices to provide better interactive user experience. This often necessitates fitting a model originally designed and trained in the cloud to edge devices with a range of hardware capabilities, which so far has relied on time-consuming manual effort. In this paper, we quantify the challenges of manually generating a large number of compressed models and then build a system framework, Mistify, to automatically port a cloud-based model to a suite of models for edge devices targeting various points in the design space. Mistify adds an intermediate “layer”more »that decouples the model design and deployment phases. By exposing configuration APIs to obviate the need for code changes deeply embedded into the original model, Mistify hides run-time issues from model designers and hides the model internals from model users, hence reducing the expertise needed in either. For better scalability, Mistify consolidates multiple model tailoring requests to minimize repeated computation. Further, Mistify leverages locally available edge data in a privacy-aware manner, and performs run-time model adaptation to provide scalable edge support and accurate inference results. Extensive evaluation shows that Mistify reduces the DNN porting time needed by over 10x to cater to a wide spectrum of edge deployment scenarios, incurring orders of magnitude less manual effort.« less
  3. Recent breakthroughs in deep learning (DL) have led to the emergence of many intelligent mobile applications and services, but in the meanwhile also pose unprecedented computing challenges on resource-constrained mobile devices. This paper builds a collaborative deep inference system between a resource-constrained mobile device and a powerful edge server, aiming at joining the power of both on-device processing and computation offloading. The basic idea of this system is to partition a deep neural network (DNN) into a front-end part running on the mobile device and a back-end part running on the edge server, with the key challenge being how tomore »locate the optimal partition point to minimize the end-to-end inference delay. Unlike existing efforts on DNN partitioning that rely heavily on a dedicated offline profiling stage to search for the optimal partition point, our system has a built-in online learning module, called Autodidactic Neurosurgeon (ANS), to automatically learn the optimal partition point on-the-fly. Therefore, ANS is able to closely follow the changes of the system environment by generating new knowledge for adaptive decision making. The core of ANS is a novel contextual bandit learning algorithm, called μLinUCB, which not only has provable theoretical learning performance guarantee but also is ultra-lightweight for easy real-world implementation. We implement our system on a video stream object detection testbed to validate the design of ANS and evaluate its performance. The experiments show that ANS significantly outperforms state-of-the-art benchmarks in terms of tracking system changes and reducing the end-to-end inference delay.« less
  4. Deep Neural Networks are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them effectively on resource-constrained mobile devices. Prior work approached the problem of support- ing deep learning in mobile applications by either decreasing model complexity or utilizing powerful cloud servers. These approaches each only focus on a single aspect of mobile inference and thus they often sacrifice overall performance. In this work we introduce a holistic approach to designing mobile deep inference frameworks. We first identify the key goals of accuracy andmore »latency for mobile deep inference and the conditions that must be met to achieve them. We demonstrate our holistic approach through the design of a hypothetical framework called MDINFERENCE. This framework leverages two complementary techniques; a model selection algorithm that chooses from a set of cloud-based deep learning models to improve inference accuracy and an on-device request duplication mechanism to bound latency. Through empirically-driven simulations we show that MDINFERENCE improves aggregate accuracy over static approaches by over 40% without incurring SLA violations. Additionally, we show that with a target latency of 250ms, MDINFERENCE increased the aggregate accuracy in 99.74% cases on faster university networks and 96.84% cases on residential networks.« less
  5. With the recent advances in both machine learning and embedded systems research, the demand to deploy computational models for real-time execution on edge devices has increased substantially. Without deploying computational models on edge devices, the frequent transmission of sensor data to the cloud results in rapid battery draining due to the energy consumption of wireless data transmission. This rapid power dissipation leads to a considerable reduction in the battery lifetime of the system, therefore jeopardizing the real-world utility of smart devices. It is well-established that for difficult machine learning tasks, models with higher performance often require more computation power andmore »thus are not power-efficient choices for deployment on edge devices. However, the trade-offs between performance and power consumption are not well studied. While numerous methods (e.g., model compression) have been developed to obtain an optimal model, these methods focus on improving the efficiency of a single model. In an entirely new direction, we introduce an effective method to find a combination of multiple models that are optimal in terms of power-efficiency and performance by solving an optimization problem in which both performance and power consumption are taken into account. Experimental results demonstrate that on the ImageNet dataset, we can achieve a 20% energy reduction with only 0.3% accuracy drop compared to Squeeze-and-Excitation Networks. Compared to a pruned convolutional neural network for human activity recognition, while consuming 1.7% less energy, our proposed policy achieves 1.3% higher accuracy.« less