Conference paper · 2019 · Open access
Towards Collaborative Intelligence Friendly Architectures for Deep Learning
International Symposium on Quality Electronic Design (ISQED), 14–19 · Published 1 March 2019 · DOI 10.1109/isqed.2019.8697647
In brief
“Towards Collaborative Intelligence Friendly Architectures for Deep Learning” is a 2019 conference paper by Amir Erfan Eshratifar and 2 co-authors, published in International Symposium on Quality Electronic Design (ISQED). OpenAlex counts 36 citations as of 19 November 2026, which puts it in the top 9% of works published in 2019 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 36
- Most cited in
- 2021 (12)
- Field-weighted impact
- 4.87
- References
- 21
- Authors
- 3
Abstract
Modern mobile devices are equipped with highperformance hardware resources such as graphics processing units (GPUs), making the end-side intelligent services more feasible. Even recently, specialized silicons as neural engines are being used for mobile devices. However, most mobile devices are still not capable of performing real-time inference using very deep models. Computations associated with deep models for today's intelligent applications are typically performed solely on the cloud. This cloud-only approach requires significant amounts of raw data to be uploaded to the cloud over the mobile wireless network and imposes considerable computational and communication load on the cloud server. Recent studies have shown that the latency and energy consumption of deep neural networks in mobile applications can be notably reduced by splitting the workload between the mobile device and the cloud. In this approach, referred to as collaborative intelligence, intermediate features computed on the mobile device are offloaded to the cloud instead of the raw input data of the network, reducing the size of the data needed to be sent to the cloud. In this paper, we design a new collaborative intelligence friendly architecture by introducing a unit responsible for reducing the size of the feature data needed to be offloaded to the cloud to a greater extent, where this unit is placed after a selected layer of a deep model. This unit is referred to as the butterfly unit. The butterfly unit consists of the reduction unit and the restoration unit. The outputs of the reduction unit is offloaded to the cloud server on which the computations associated with the restoration unit and the rest of the inference network are performed. Both the reduction and restoration units use a convolutional layer as their main component. The inference outcomes are sent back to the mobile device. The new network architecture, including the introduced butterfly unit after a selected layer of the underlying deep model, is trained end-to-end. Our proposed method, across different wireless networks, achieves on average 53x improvements for end-to-end latency and 68 x improvements for mobile energy consumption compared to the status quo cloud-only approach for ResNet-50, while the accuracy loss is less than 2 %.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Eshratifar, A. E., Esmaili, A., & Pedram, M. (2019). Towards Collaborative Intelligence Friendly Architectures for Deep Learning. International Symposium on Quality Electronic Design (ISQED), 14–19. https://doi.org/10.1109/isqed.2019.8697647
MLA 9
Eshratifar, Amir Erfan, et al. “Towards Collaborative Intelligence Friendly Architectures for Deep Learning.” International Symposium on Quality Electronic Design (ISQED), 2019, pp. 14–19. https://doi.org/10.1109/isqed.2019.8697647.
Chicago
Eshratifar, Amir Erfan, Amirhossein Esmaili, and Massoud Pedram. 2019. “Towards Collaborative Intelligence Friendly Architectures for Deep Learning.” International Symposium on Quality Electronic Design (ISQED): 14–19. https://doi.org/10.1109/isqed.2019.8697647.
Harvard
Eshratifar, A. E., Esmaili, A. and Pedram, M. (2019) ‘Towards Collaborative Intelligence Friendly Architectures for Deep Learning’, International Symposium on Quality Electronic Design (ISQED), pp. 14–19. doi:10.1109/isqed.2019.8697647.
IEEE
A. E. Eshratifar, A. Esmaili, and M. Pedram, “Towards Collaborative Intelligence Friendly Architectures for Deep Learning,” International Symposium on Quality Electronic Design (ISQED), pp. 14–19, 2019, doi: 10.1109/isqed.2019.8697647.
BibTeX
@inproceedings{eshratifar2019towards,
title = {{Towards Collaborative Intelligence Friendly Architectures for Deep Learning}},
author = {Eshratifar, Amir Erfan and Esmaili, Amirhossein and Pedram, Massoud},
booktitle = {International Symposium on Quality Electronic Design (ISQED)},
year = {2019},
pages = {14--19},
doi = {10.1109/isqed.2019.8697647},
url = {https://doi.org/10.1109/isqed.2019.8697647}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2019 | 2 | |
| 2020 | 8 | |
| 2021 | 12 | |
| 2022 | 5 | |
| 2023 | 2 | |
| 2024 | 3 | |
| 2025 | 3 | |
| 2026 | 1 |
Its field-weighted citation impact is 4.87: it has been cited 4.87 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- collaborative intelligence
- mobile edge computing
- cloud offloading
- butterfly unit
- feature reduction
- convolutional layers
- latency reduction
- energy consumption
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Eshratifar, A. E., Esmaili, A., & Pedram, M. (2019). Towards Collaborative Intelligence Friendly Architectures for Deep Learning. International Symposium on Quality Electronic Design (ISQED), 14–19. https://doi.org/10.1109/isqed.2019.8697647
How many times has this paper been cited?
36 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Amir Erfan Eshratifar, Amirhossein Esmaili, Massoud Pedram.
What is the DOI of this paper?
10.1109/isqed.2019.8697647, permanently at https://doi.org/10.1109/isqed.2019.8697647. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.