More Web Proxy on the site http://driver.im/

research-article

Open access

MTL-Split: Multi-Task Learning for Edge Devices using Split Computing

Authors:

Luigi Capogrosso,

Enrico Fraccaroli,

Samarjit Chakraborty,

Marco CristaniAuthors Info & Claims

DAC '24: Proceedings of the 61st ACM/IEEE Design Automation Conference

Article No.: 261, Pages 1 - 6

https://doi.org/10.1145/3649329.3655686

Published: 07 November 2024 Publication History

Abstract

Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split.

References

[1]

Firoj Alam, Tanvirul Alam, Md Arid Hasan, Abul Hasnat, Muhammad Imran, and Ferda Ofli. 2023. MEDIC: a multi-task learning dataset for disaster image classification. Neural Computing and Applications 35, 3 (2023), 2609--2632.

Digital Library

[2]

Etienne Boursier, Mikhail Konobeev, and Nicolas Flammarion. 2022. Trace norm regularization for multi-task learning with scarce data. In Conference on Learning Theory. PMLR, 1303--1327.

[3]

Chris Burgess and Hyunjik Kim. 2018. 3D Shapes Dataset. https://github.com/deepmind/3dshapes-dataset/.

[4]

Luigi Capogrosso, Federico Cunico, Dong Seon Cheng, Franco Fummi, and Marco Cristani. 2024. A Machine Learning-oriented Survey on Tiny Machine Learning. IEEE Access (2024).

[5]

Luigi Capogrosso, Federico Cunico, Michele Lora, Marco Cristani, Franco Fummi, and Davide Quaglia. 2023. Split-Et-Impera: A Framework for the Design of Distributed Deep Learning Applications. In 2023 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS). IEEE, 39--44.

[6]

Rich Caruana. 1997. Multitask learning. Machine learning 28 (1997), 41--75.

Digital Library

[7]

Hyomin Choi and Ivan V Bajić. 2018. Deep feature compression for collaborative object detection. In 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 3743--3747.

[8]

Federico Cunico, Luigi Capogrosso, Francesco Setti, Damiano Carra, Franco Fummi, and Marco Cristani. 2022. I-split: Deep network interpretability for split computing. In 2022 26th International Conference on Pattern Recognition (ICPR). IEEE, 2575--2581.

[9]

Natalie C Ebner, Michaela Riediger, and Ulman Lindenberger. 2010. FACES---A database of facial expressions in young, middle-aged, and older women and men: Development and validation. Behavior research methods 42 (2010), 351--362.

[10]

Amir Erfan Eshratifar, Mohammad Saeed Abrishami, and Massoud Pedram. 2019. JointDNN: An efficient training and inference engine for intelligent mobile cloud computing services. IEEE Transactions on Mobile Computing 20, 2 (2019), 565--576.

Digital Library

[11]

Amir Erfan Eshratifar, Amirhossein Esmaili, and Massoud Pedram. 2019. Bottlenet: A deep learning architecture for intelligent mobile cloud computing services. In 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED). IEEE, 1--6.

[12]

Yuan Gao, Jiayi Ma, Mingbo Zhao, Wei Liu, and Alan L Yuille. 2019. Nddr-cnn: Layerwise feature fusing in multi-task cnns by neural discriminative dimensionality reduction. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3205--3214.

[13]

Jianping Gou, Baosheng Yu, Stephen J Maybank, and Dacheng Tao. 2021. Knowledge distillation: A survey. International Journal of Computer Vision 129 (2021), 1789--1819.

Digital Library

[14]

Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, et al. 2019. Searching for mobilenetv3. In Proceedings of the IEEE/CVF international conference on computer vision. 1314--1324.

[15]

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

[16]

Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491.

[17]

Guangli Li, Lei Liu, Xueying Wang, Xiao Dong, Peng Zhao, and Xiaobing Feng. 2018. Auto-tuning neural network quantization framework for collaborative inference between the cloud and edge. In Artificial Neural Networks and Machine Learning-ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part I 27. Springer, 402--411.

[18]

Tailin Liang, John Glossner, Lei Wang, Shaobo Shi, and Xiaotong Zhang. 2021. Pruning and quantization for deep neural network acceleration: A survey. Neurocomputing 461 (2021), 370--403.

Digital Library

[19]

Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017).

[20]

Yoshitomo Matsubara, Sabur Baidya, Davide Callegaro, Marco Levorato, and Sameer Singh. 2019. Distilled split deep neural networks for edge-assisted realtime systems. In Proceedings of the 2019 Workshop on Hot Topics in Video Analytics and Intelligent Edges. 21--26.

Digital Library

[21]

Yoshitomo Matsubara, Marco Levorato, and Francesco Restuccia. 2022. Split computing and early exiting for deep learning applications: Survey and research challenges. Comput. Surveys 55, 5 (2022), 1--30.

Digital Library

[22]

Aviv Navon, Aviv Shamsian, Idan Achituve, Haggai Maron, Kenji Kawaguchi, Gal Chechik, and Ethan Fetaya. 2022. Multi-Task Learning as a Bargaining Game. In International Conference on Machine Learning. PMLR, 16428--16446.

[23]

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019).

[24]

Marion Sbai, Muhamad Risqi U Saputra, Niki Trigoni, and Andrew Markham. 2021. Cut, distil and encode (cde): Split cloud-edge deep inference. In 2021 18th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE, 1--9.

Digital Library

[25]

Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems 31 (2018).

[26]

Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).

[27]

Trevor Standley, Amir Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, and Silvio Savarese. 2020. Which tasks should be learned together in multi-task learning?. In International Conference on Machine Learning. PMLR, 9120--9132.

[28]

Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114.

[29]

Xiaogang Xu, Hengshuang Zhao, Vibhav Vineet, Ser-Nam Lim, and Antonio Torralba. 2022. Mtformer: Multi-task learning via transformer and cross-task reasoning. In European Conference on Computer Vision. Springer, 304--321.

Digital Library

[30]

Amir R Zamir, Alexander Sax, William Shen, Leonidas J Guibas, Jitendra Malik, and Silvio Savarese. 2018. Taskonomy: Disentangling task transfer learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3712--3722.

[31]

Jianfeng Zhang, Wensheng Zhang, and Jingdong Xu. 2022. Bandwidth-efficient multi-task AI inference with dynamic task importance for the Internet of Things in edge computing. Computer Networks 216 (2022), 109262.

Digital Library

Cited By

Capogrosso LXu SFraccaroli ECristani MFummi FChakraborty S(2024)Learning-Enabled CPS for Edge-Cloud Computing2024 IEEE 14th International Symposium on Industrial Embedded Systems (SIES)10.1109/SIES62473.2024.10767956(132-139)Online publication date: 23-Oct-2024
https://doi.org/10.1109/SIES62473.2024.10767956
Capogrosso LFraccaroli EPetrozziello GSetti FChakraborty SFummi FCristani M(2024)Enhancing Split Computing and Early Exit Applications through Predefined Sparsity2024 Forum on Specification & Design Languages (FDL)10.1109/FDL63219.2024.10673767(1-8)Online publication date: 4-Sep-2024
https://doi.org/10.1109/FDL63219.2024.10673767

Index Terms

MTL-Split: Multi-Task Learning for Edge Devices using Split Computing
1. Computer systems organization
  1. Architectures
    1. Other architectures
      1. Neural networks
2. Computing methodologies
  1. Distributed computing methodologies
    1. Distributed algorithms
  2. Machine learning

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

Recommendations

Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire ...
Evolving Deep Parallel Neural Networks for Multi-Task Learning
Algorithms and Architectures for Parallel Processing
Abstract
Multi-Task Learning (MTL) can perform multiple tasks simultaneously with a single model, and can achieve competitive performance for each individual task. In recent years, the Deep Neural Networks (DNNs) based models have demonstrated their ...
Enhanced task attention with adversarial learning for dynamic multi-task CNN
Highlights
- We propose a novel learning framework of multi-task CNN to enhance task attention through tuning the TTC of the shared subnet DMT-CNN with adversarial ...
Abstract
Multi-task deep learning is promising to solve multi-label multi-instance visual recognition tasks. However, flexible information sharing in the task group might bring performance bottlenecks to an individual task. To tackle this ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

DAC '24: Proceedings of the 61st ACM/IEEE Design Automation Conference

June 2024

2159 pages

ISBN:9798400706011

DOI:10.1145/3649329

Chair:
Vivek De

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGDA: ACM Special Interest Group on Design Automation
IEEE-CEDA

In-Cooperation

SIGBED: ACM Special Interest Group on Embedded Systems

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 November 2024

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

HORIZON EUROPE Marie Sklodowska-Curie Actions
Italy's recovery and resilience plan

Conference

DAC '24

Sponsor:

SIGDA

DAC '24: 61st ACM/IEEE Design Automation Conference

June 23 - 27, 2024

CA, San Francisco, USA

Acceptance Rates

Overall Acceptance Rate 1,770 of 5,499 submissions, 32%

Upcoming Conference

DAC '25

Sponsor:
sigda

62nd ACM/IEEE Design Automation Conference

June 22 - 26, 2025

San Francisco , CA , USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
75
Total Downloads

Downloads (Last 12 months)75
Downloads (Last 6 weeks)75

Reflects downloads up to 13 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Capogrosso LXu SFraccaroli ECristani MFummi FChakraborty S(2024)Learning-Enabled CPS for Edge-Cloud Computing2024 IEEE 14th International Symposium on Industrial Embedded Systems (SIES)10.1109/SIES62473.2024.10767956(132-139)Online publication date: 23-Oct-2024
https://doi.org/10.1109/SIES62473.2024.10767956
Capogrosso LFraccaroli EPetrozziello GSetti FChakraborty SFummi FCristani M(2024)Enhancing Split Computing and Early Exit Applications through Predefined Sparsity2024 Forum on Specification & Design Languages (FDL)10.1109/FDL63219.2024.10673767(1-8)Online publication date: 4-Sep-2024
https://doi.org/10.1109/FDL63219.2024.10673767

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

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

Media

Figures

Other

Tables

View Table of Contents