paper-with-me

Papers

Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint

2021-12-21 · Andrea Fresa, Jaya Prakash Champati

With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using Machine Learning (ML) inference, we study the problem of offloading inference jobs by considering the following novel aspects: 1) in contrast to a typical computational job, the processing time of an inference job depends on the size of the ML model, and 2) recently proposed Deep Neural Networks (DNNs) for resource-constrained devices provide the choice of scaling the model size. We formulate an assignment problem with the aim of maximizing the total inference accuracy of n data samples available at the ED, subject to a time constraint T on the makespan. We propose an approximation algorithm AMR2, and prove that it results in a makespan at most 2T, and achieves a total accuracy that is lower by a small constant from optimal total accuracy. As proof of concept, we implemented AMR2 on a Raspberry Pi, equipped with MobileNet, and is connected to a server equipped with ResNet, and studied the total accuracy and makespan performance of AMR2 for image classification application.

📄 PDF Abstract BibTeX arXiv:2112.11413

Code (0)

등록된 구현이 없습니다.

Tasks

Edge-computingimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing

2022-10-24 · Nan Li, Alexandros Iosifidis, Qi Zhang

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and Edge servers' available capacity, we use earl…

Decision MakingDeep Reinforcement LearningEdge-computingreinforcement-learning+2

Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder

2024-01-19 · Nan Li, Alexandros Iosifidis, Qi Zhang

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and computation resource availability, we propose…

Decision MakingDecoderEdge-computingFeature Compression+1

Lessons Learned from Accident of Autonomous Vehicle Testing: An Edge Learning-aided Offloading Framework

2020-06-27 · Bo Yang, Xuelin Cao, Xiangfang Li, Chau Yuen 외

This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency const…

Autonomous Driving

Joint Optimization of DNN Inference Delay and Energy under Accuracy Constraints for AR Applications

2022-08-03 · Guangjin Pan, Heng Zhang, Shugong Xu, Shunqing Zhang 외

The high computational complexity and high energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. This paper considers the scene of completing video-base…

Edge-computingScheduling

Early-exit deep neural networks for distorted images: providing an efficient edge offloading

2021-08-20 · Roberto G. Pacheco, Fernanda D. V. R. Oliveira, Rodrigo S. Couto

Edge offloading for deep neural networks (DNNs) can be adaptive to the input's complexity by using early-exit DNNs. These DNNs have side branches throughout their architecture, allowing the inference to end earlier in th…

image-classificationImage Classification