research-article

Pyramid: Enabling Hierarchical Neural Networks with Edge Computing

Authors:

Shuiguang Deng,

Yun YangAuthors Info & Claims

WWW '22: Proceedings of the ACM Web Conference 2022

Pages 1860 - 1870

https://doi.org/10.1145/3485447.3511990

Published: 25 April 2022 Publication History

Abstract

Machine learning (ML) is powering a rapidly-increasing number of web applications. As a crucial part of 5G, edge computing facilitates edge artificial intelligence (AI) by ML model training and inference at the network edge on edge servers. Compared with centralized cloud AI, edge AI enables low-latency ML inference which is critical to many delay-sensitive web applications, e.g., web AR/VR, web gaming and Web-of-Things applications. Existing studies of edge AI focused on resource and performance optimization in training and inference, leveraging edge computing merely as a tool to accelerate training and inference processes. However, the unique ability of edge computing to process data with context awareness, a powerful feature for building the web-of-things for smart cities, has not been properly explored. In this paper, we propose a novel framework named Pyramid that unleashes the potential of edge AI by facilitating homogeneous and heterogeneous hierarchical ML inferences. We motivate and present Pyramid with traffic prediction as an illustrative example, and evaluate it through extensive experiments conducted on two real-world datasets. The results demonstrate the superior performance of Pyramid neural networks in hierarchical traffic prediction and weather analysis.

References

[1]

L Bai, L Yao, C Li, X Wang, and C Wang. 2020. Adaptive graph convolutional recurrent network for traffic forecasting. In 34th Conference on Neural Information Processing Systems.

Digital Library

[2]

Léon Bottou. 2010. Large-scale machine learning with stochastic gradient descent. In 19th International Conference on Computational Statistics. 177–186.

[3]

Chao Chen, Karl Petty, Alexander Skabardonis, Pravin Varaiya, and Zhanfeng Jia. 2001. Freeway performance measurement system: mining loop detector data. Transportation Research Record 1748, 1 (2001), 96–102.

[4]

Jiasi Chen and Xukan Ran. 2019. Deep learning with edge computing: a review. Proc. IEEE 107, 8 (2019), 1655–1674.

[5]

Min Chen, Haichuan Wang, Zeyu Meng, Hongli Xu, Yang Xu, Jianchun Liu, and He Huang. 2020. Joint data collection and resource allocation for distributed machine learning at the edge. IEEE Transactions on Mobile Computing(2020). https://doi.org/10.1109/TMC.2020.3045436

Digital Library

[6]

Wenlin Chen, James Wilson, Stephen Tyree, Kilian Weinberger, and Yixin Chen. 2015. Compressing neural networks with the hashing trick. In International Conference on Machine Learning. PMLR, 2285–2294.

[7]

Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Conference on Empirical Methods in Natural Language Processing. 1724–1734.

[8]

Yann N Dauphin, Angela Fan, Michael Auli, and David Grangier. 2017. Language modeling with gated convolutional networks. In International Conference on Machine Learning. PMLR, 933–941.

[9]

Jeffrey Dean, Greg S Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Quoc V Le, Mark Z Mao, Marc’Aurelio Ranzato, Andrew Senior, Paul Tucker, 2012. Large scale distributed deep networks. In 25th International Conference on Neural Information Processing Systems. 1223–1231.

[10]

Sayda Elmi and Kian-Lee Tan. 2021. DeepFEC: energy consumption prediction under real-world driving conditions for smart cities. In The Web Conference. 1880–1890.

Digital Library

[11]

Kan Guo, Yongli Hu, Yanfeng Sun, Sean Qian, Junbin Gao, and Baocai Yin. 2021. Hierarchical graph convolution networks for traffic forecasting. In 36th AAAI Conference on Artificial Intelligence, Vol. 35. 151–159.

[12]

Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In AAAI Conference on Artificial Intelligence. 922–929.

Digital Library

[13]

Jindong Han, Hao Liu, Hengshu Zhu, Hui Xiong, and Dejing Dou. 2021. Joint air quality and weather prediction based on multi-adversarial spatiotemporal networks. In 35th AAAI Conference on Artificial Intelligence. 4081–4089.

[14]

Rui Han, Shilin Li, Xiangwei Wang, Chi Harold Liu, Gaofeng Xin, and Lydia Y Chen. 2021. Accelerating Gossip-based Deep Learning in Heterogeneous Edge Computing Platforms. IEEE Transactions on Parallel and Distributed Systems 32, 7 (2021), 1591–1602.

[15]

Andrew Hard, Kanishka Rao, Rajiv Mathews, Swaroop Ramaswamy, Françoise Beaufays, Sean Augenstein, Hubert Eichner, Chloé Kiddon, and Daniel Ramage. 2018. Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604(2018).

[16]

Qiang He, Guangming Cui, Xuyun Zhang, Feifei Chen, Shuiguang Deng, Hai Jin, Yanhui Li, and Yun Yang. 2019. A game-theoretical approach for user allocation in edge computing environment. IEEE Transactions on Parallel and Distributed Systems 31, 3 (2019), 515–529.

[17]

István Hegedűs, Gábor Danner, and Márk Jelasity. 2019. Gossip learning as a decentralized alternative to federated learning. In IFIP International Conference on Distributed Applications and Interoperable Systems. Springer, 74–90.

Digital Library

[18]

Chuang Hu, Wei Bao, Dan Wang, and Fengming Liu. 2019. Dynamic adaptive DNN surgery for inference acceleration on the edge. In IEEE INFOCOM Conference on Computer Communications. IEEE, 1423–1431.

Digital Library

[19]

Yun Chao Hu, Milan Patel, Dario Sabella, Nurit Sprecher, and Valerie Young. 2015. Mobile edge computing—a key technology towards 5G. ETSI white paper 11, 11 (2015), 1–16.

[20]

Rongzhou Huang, Chuyin Huang, Yubao Liu, Genan Dai, and Weiyang Kong. 2020. LSGCN: long short-term traffic prediction with graph convolutional networks. In International Joint Conference on Artificial Intelligence. 2355–2361.

[21]

Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. PMLR, 448–456.

[22]

Yiping Kang, Johann Hauswald, Cao Gao, Austin Rovinski, Trevor Mudge, Jason Mars, and Lingjia Tang. 2017. Neurosurgeon: collaborative intelligence between the cloud and mobile edge. ACM SIGARCH Computer Architecture News 45, 1 (2017), 615–629.

Digital Library

[23]

Diederik P Kingma and Jimmy Ba. 2014. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014).

[24]

Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations. 61––80.

[25]

Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436–444.

[26]

Seunghak Lee, Jin Kyu Kim, Xun Zheng, Qirong Ho, Garth A Gibson, and Eric P Xing. 2014. On model parallelization and scheduling strategies for distributed machine learning. In 27th International Conference on Neural Information Processing Systems. 2834–2842.

[27]

Mu Li, David G Andersen, Jun Woo Park, Alexander J Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene J Shekita, and Bor-Yiing Su. 2014. Scaling distributed machine learning with the parameter server. In 11th USENIX Symposium on Operating Systems Design and Implementation). 583–598.

Digital Library

[28]

Tian Li, Anit Kumar Sahu, Ameet Talwalkar, and Virginia Smith. 2020. Federated learning: challenges, methods, and future directions. IEEE Signal Processing Magazine 37, 3 (2020), 50–60.

[29]

Youjie Li, Mingchao Yu, Songze Li, Salman Avestimehr, Nam Sung Kim, and Alexander Schwing. 2018. Pipe-SGD: a decentralized pipelined SGD framework for distributed deep net training. In 32nd International Conference on Neural Information Processing Systems. 8056–8067.

[30]

Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2017. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926(2017).

[31]

Yuxuan Liang, Kun Ouyang, Junkai Sun, Yiwei Wang, Junbo Zhang, Yu Zheng, David Rosenblum, and Roger Zimmermann. 2021. Fine-grained urban flow prediction. In The Web Conference. 1833–1845.

Digital Library

[32]

Yuhua Lin and Haiying Shen. 2017. CloudFog: Leveraging fog to extend cloud gaming for thin-client MMOG with high quality of service. IEEE Transactions on Parallel and Distributed Systems2 (2017), 431–445.

[33]

Chang Liu, Yu Cao, Yan Luo, Guanling Chen, Vinod Vokkarane, Ma Yunsheng, Songqing Chen, and Peng Hou. 2017. A new deep learning-based food recognition system for dietary assessment on an edge computing service infrastructure. IEEE Transactions on Services Computing 11, 2 (2017), 249–261.

[34]

Luyang Liu, Hongyu Li, and Marco Gruteser. 2019. Edge assisted real-time object detection for mobile augmented reality. In 25th Annual International Conference on Mobile Computing and Networking. 1–16.

Digital Library

[35]

Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, and Changshui Zhang. 2017. Learning efficient convolutional networks through network slimming. In IEEE International Conference on Computer Vision. 2736–2744.

[36]

Zongqing Lu, Swati Rallapalli, Kevin S Chan, Shiliang Pu, and Tom La Porta. 2021. Augur: modeling the resource requirements of ConvNets on mobile devices. IEEE Transactions on Mobile Computing 107, 2 (2021), 352–365.

Digital Library

[37]

Yisheng Lv, Yanjie Duan, Wenwen Kang, Zhengxi Li, and Fei-Yue Wang. 2014. Traffic flow prediction with big data: a deep learning approach. IEEE Transactions on Intelligent Transportation Systems 16, 2(2014), 865–873.

[38]

Yuyi Mao, Changsheng You, Jun Zhang, Kaibin Huang, and Khaled B Letaief. 2017. A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials 19, 4 (2017), 2322–2358.

[39]

Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics. PMLR, 1273–1282.

[40]

Benedikt Ostermaier, Kay Römer, Friedemann Mattern, Michael Fahrmair, and Wolfgang Kellerer. 2010. A real-time search engine for the web of things. In 2010 Internet of Things (IOT). IEEE, 1–8.

[41]

Zheyi Pan, Songyu Ke, Xiaodu Yang, Yuxuan Liang, Yong Yu, Junbo Zhang, and Yu Zheng. 2021. AutoSTG: neural architecture search for predictions of spatio-temporal graph. In Web Conference. 1846–1855.

Digital Library

[42]

Jihong Park, Sumudu Samarakoon, Mehdi Bennis, and Mérouane Debbah. 2019. Wireless network intelligence at the edge. Proc. IEEE 107, 11 (2019), 2204–2239.

[43]

Xiuquan Qiao, Pei Ren, Schahram Dustdar, Ling Liu, Huadong Ma, and Junliang Chen. 2019. Web AR: A promising future for mobile augmented reality—State of the art, challenges, and insights. Proc. IEEE 107, 4 (2019), 651–666.

[44]

Yuanming Shi, Kai Yang, Tao Jiang, Jun Zhang, and Khaled B Letaief. 2020. Communication-efficient edge AI: algorithms and systems. IEEE Communications Surveys & Tutorials 22, 4 (2020), 2167–2191.

[45]

Hoo-Chang Shin, Matthew R Orton, David J Collins, Simon J Doran, and Martin O Leach. 2012. Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 8(2012), 1930–1943.

Digital Library

[46]

Alex J Smola and Bernhard Schölkopf. 2004. A tutorial on support vector regression. Statistics and Computing 14, 3 (2004), 199–222.

Digital Library

[47]

Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In 27th International Conference on Neural Information Processing Systems. 3104–3112.

[48]

Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2016. Branchynet: Fast inference via early exiting from deep neural networks. In 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2464–2469.

[49]

Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2017. Distributed deep neural networks over the cloud, the edge and end devices. In 37th IEEE International Conference on Distributed Computing Systems. IEEE, 328–339.

[50]

Xiaoyang Wang, Yao Ma, Yiqi Wang, Wei Jin, Xin Wang, Jiliang Tang, Caiyan Jia, and Jian Yu. 2020. Traffic flow prediction via spatial temporal graph neural network. In The Web Conference. 1082–1092.

Digital Library

[51]

Billy M Williams and Lester A Hoel. 2003. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results. Journal of Transportation Engineering 129, 6 (2003), 664–672.

[52]

Carole-Jean Wu, David Brooks, Kevin Chen, Douglas Chen, Sy Choudhury, Marat Dukhan, Kim Hazelwood, Eldad Isaac, Yangqing Jia, Bill Jia, 2019. Machine learning at Facebook: understanding inference at the edge. In IEEE International Symposium on High Performance Computer Architecture. IEEE, 331–344.

[53]

Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng. 2016. Quantized convolutional neural networks for mobile devices. In IEEE Conference on Computer Vision and Pattern Recognition. 4820–4828.

[54]

Z Wu, S Pan, G Long, J Jiang, and C Zhang. 2019. Graph WaveNet for deep spatial-temporal graph modeling. In 28th International Joint Conference on Artificial Intelligence (IJCAI). 1907–1913.

[55]

Huaxiu Yao, Yiding Liu, Ying Wei, Xianfeng Tang, and Zhenhui Li. 2019. Learning from multiple cities: a meta-learning approach for spatial-temporal prediction. In The Web Conference. 2181–2191.

Digital Library

[56]

Bing Yu, Haoteng Yin, and Zhanxing Zhu. 2018. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In 27th International Joint Conference on Artificial Intelligence. 3634–3640.

[57]

Liang Yuan, Qiang He, Siyu Tan, Bo Li, Jiangshan Yu, Feifei Chen, Hai Jin, and Yun Yang. 2021. CoopEdge: A Decentralized Blockchain-based Platform for Cooperative Edge Computing. In The Web Conference. 2245–2257. https://doi.org/10.1145/3442381.3449994

Digital Library

[58]

Letian Zhang, Lixing Chen, and Jie Xu. 2021. Autodidactic Neurosurgeon: collaborative deep inference for mobile edge intelligence via online learning. In The Web Conference. 3111–3123.

Digital Library

[59]

Xiyue Zhang, Chao Huang, Yong Xu, Lianghao Xia, Peng Dai, Liefeng Bo, Junbo Zhang, and Yu Zheng. 2020. Traffic flow forecasting with spatial-temporal graph diffusion network. In 35th AAAI Conference on Artificial Intelligence. 15008–15015.

[60]

Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun. 2018. Shufflenet: an extremely efficient convolutional neural network for mobile devices. In IEEE Conference on computer Vision and Pattern Recognition. 6848–6856.

[61]

Zhenyu Zhou, Haijun Liao, Bo Gu, Kazi Mohammed Saidul Huq, Shahid Mumtaz, and Jonathan Rodriguez. 2018. Robust mobile crowd sensing: when deep learning meets edge computing. IEEE Network 32, 4 (2018), 54–60.

Digital Library

Cited By

Trigka MDritsas E(2025)Edge and Cloud Computing in Smart CitiesFuture Internet10.3390/fi1703011817:3(118)Online publication date: 6-Mar-2025
https://doi.org/10.3390/fi17030118
Luo RHe QChen FWu SJin HYang Y(2025)Ripple: Enabling Decentralized Data Deduplication at the EdgeIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2024.349395336:1(55-66)Online publication date: Jan-2025
https://doi.org/10.1109/TPDS.2024.3493953
Li YZhao PMa XYuan HFu ZXu MWang S(2025)A Collaborative Cloud-Edge Approach for Robust Edge Workload ForecastingIEEE Transactions on Mobile Computing10.1109/TMC.2024.350268324:4(2861-2875)Online publication date: Apr-2025
https://doi.org/10.1109/TMC.2024.3502683
Show More Cited By

Index Terms

Pyramid: Enabling Hierarchical Neural Networks with Edge Computing

Index terms have been assigned to the content through auto-classification.

Recommendations

Edge AI: A Taxonomy, Systematic Review and Future Directions
Abstract
Edge Artificial Intelligence (AI) incorporates a network of interconnected systems and devices that receive, cache, process, and analyse data in close communication with the location where the data is captured with AI technology. Recent ...
Edge Intelligence: Concepts, Architectures, Applications, and Future Directions
The name edge intelligence, also known as Edge AI, is a recent term used in the past few years to refer to the confluence of machine learning, or broadly speaking artificial intelligence, with edge computing. In this article, we revise the concepts ...
In-network placement of delay-constrained computing tasks in a softwarized intelligent edge
Abstract
Future sixth-generation (6G) networks will rely on the synergies of edge computing and machine learning (ML) to build an intelligent edge, where communication and computing resources will be jointly orchestrated. In this work, we ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

WWW '22: Proceedings of the ACM Web Conference 2022

April 2022

3764 pages

ISBN:9781450390965

DOI:10.1145/3485447

Editors:
Frédérique Laforest
INSA Lyon, France
,
Raphaël Troncy
EURECOM, France
,
Elena Simperl
King’s College London, UK
,
Deepak Agarwal
Pinterest, USA
,
Aristides Gionis
KTH Royal Institute of Technology, Sweden
,
Ivan Herman
W3C / retired
,
Lionel Médini
Université Lyon 1, France

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 April 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

WWW '22

Sponsor:

SIGWEB

WWW '22: The ACM Web Conference 2022

April 25 - 29, 2022

Virtual Event, Lyon, France

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

58
Total Citations
View Citations
1,024
Total Downloads

Downloads (Last 12 months)183
Downloads (Last 6 weeks)16

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Trigka MDritsas E(2025)Edge and Cloud Computing in Smart CitiesFuture Internet10.3390/fi1703011817:3(118)Online publication date: 6-Mar-2025
https://doi.org/10.3390/fi17030118
Luo RHe QChen FWu SJin HYang Y(2025)Ripple: Enabling Decentralized Data Deduplication at the EdgeIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2024.349395336:1(55-66)Online publication date: Jan-2025
https://doi.org/10.1109/TPDS.2024.3493953
Li YZhao PMa XYuan HFu ZXu MWang S(2025)A Collaborative Cloud-Edge Approach for Robust Edge Workload ForecastingIEEE Transactions on Mobile Computing10.1109/TMC.2024.350268324:4(2861-2875)Online publication date: Apr-2025
https://doi.org/10.1109/TMC.2024.3502683
Li BFan HGao YDong W(2025)WaWoT: Towards Flexible and Efficient Web of Things Services via WebAssembly on Resource-Constrained IoT DevicesIEEE Transactions on Computers10.1109/TC.2024.350038574:3(1094-1108)Online publication date: Mar-2025
https://doi.org/10.1109/TC.2024.3500385
Dou SGuo Z(2025)Maintaining Predictable Traffic Engineering Performance Under Controller Failures for Software-Defined WANsIEEE Journal on Selected Areas in Communications10.1109/JSAC.2025.352881443:2(524-536)Online publication date: Feb-2025
https://doi.org/10.1109/JSAC.2025.3528814
Zhong KLi QRen ATan YChen XLong LLiu D(2025)PIM-IoT: Enabling hierarchical, heterogeneous, and agile Processing-in-Memory in IoT systemsFuture Generation Computer Systems10.1016/j.future.2025.107782169(107782)Online publication date: Aug-2025
https://doi.org/10.1016/j.future.2025.107782
Liu WXu XWu JJiang J(2024)Federated Meta Reinforcement Learning for Personalized TasksTsinghua Science and Technology10.26599/TST.2023.901006629:3(911-926)Online publication date: Jun-2024
https://doi.org/10.26599/TST.2023.9010066
Cai QCao JChen YQian SYuan LWang J(2024)PREFER: A Pre-trained Model Recommendation Framework for Edge Computing Enabled Traffic Flow PredictionACM Transactions on Knowledge Discovery from Data10.1145/370746419:2(1-26)Online publication date: 9-Dec-2024
https://dl.acm.org/doi/10.1145/3707464
Dou SQi LGuo ZChua TNgo CKa-Wei Lee RKumar RLauw H(2024)ARES: Predictable Traffic Engineering under Controller Failures in SD-WANsProceedings of the ACM Web Conference 202410.1145/3589334.3645321(2703-2712)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645321
Fu SDong FShen DZhang JHuang ZHe Q(2024)Joint Optimization of Device Selection and Resource Allocation for Multiple Federations in Federated Edge LearningIEEE Transactions on Services Computing10.1109/TSC.2023.334243517:1(251-262)Online publication date: Jan-2024
https://doi.org/10.1109/TSC.2023.3342435
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten