Proceedings Article10.1145/3404397.3404473
Adaptive Distributed Convolutional Neural Network Inference at the Network Edge with ADCNN
Sai Qian Zhang,Jieyu Lin,Qi Zhang +2 more
- 17 Aug 2020
29
TL;DR: This paper studies the problem of distributed execution of inference tasks on edge clusters for Convolutional Neural Networks (CNNs), one of the most prominent models of DNN, and presents Fully Decomposable Spatial Partition (FDSP), which naturally supports resource heterogeneity and dynamicity in edge computing environments.
read more
Abstract: The emergence of the Internet of Things (IoT) has led to a remarkable increase in the volume of data generated at the network edge. In order to support real-time smart IoT applications, massive amounts of data generated from edge devices need to be processed using methods such as deep neural networks (DNNs) with low latency. To improve application performance and minimize resource cost, enterprises have begun to adopt Edge computing, a computation paradigm that advocates processing input data locally at the network edge. However, as edge nodes are often resource-constrained, running data-intensive DNN inference tasks on each individual edge node often incurs high latency, which seriously limits the practicality and effectiveness of this model. In this paper, we study the problem of distributed execution of inference tasks on edge clusters for Convolutional Neural Networks (CNNs), one of the most prominent models of DNN. Unlike previous work, we present Fully Decomposable Spatial Partition (FDSP), which naturally supports resource heterogeneity and dynamicity in edge computing environments. We then present a compression technique that further reduces network communication overhead. Our system, called ADCNN, provides up to 2.8 × speed up compared to state-of-the-art approaches, while achieving a competitive inference accuracy.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
CNN Partitioning and Offloading for Vehicular Edge Networks in Web3
TL;DR: In this article , a dynamic offloading strategy based on game theory combined with convolutional neural network (CNN) partition for vehicular edge networks, named GPOV, is proposed.
45
DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices
Xueyu Hou,Yongjie Guan,Tao Han,Ning Zhang +3 more
- 03 Feb 2022
TL;DR: This work proposes a general method, called DistrEdge, to provide CNN inference distribution strategies in environments with multiple IoT edge devices, and shows that it achieves 1.1 to 3 x speedup compared to state-of-the-art methods.
Multi-Relay Assisted Computation Offloading for Multi-Access Edge Computing Systems With Energy Harvesting
TL;DR: In this article, a multi-relay assisted computation offloading framework for MEC-EH systems is proposed, where a computation task can be executed by offloading to the MEC server with the help of multiple relay nodes, such as the neighboring nodes.
34
Joint multi-user DNN partitioning and task offloading in mobile edge computing
TL;DR: In this article , the authors proposed a partitioning and offloading scheme for heterogeneous tasks-server system to reduce the overall system latency and energy consumption on DNN inference, which is based on the partition points, an offloading of DNN tasks for each MD is presented to finish the whole scheme.
21
Joint DNN Partition and Resource Allocation for Task Offloading in Edge-Cloud-Assisted IoT Environments
15 Jun 2023
TL;DR: In this paper , a multi-base station (BS) and multi-service edge-cloud-assisted IoT environment, where both the BSs and the cloud can assist the IoT devices to process multi-type Deep Learning (DL) tasks via task offloading, is considered.
20
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K