Differentiable Transportation Pruning

Yunqiang Li; Jan C. van Gemert; Torsten  Hoefler; Bert Moons; Evangelos  Eleftheriou; Bram-Ernst  Verhoef

doi:10.1109/ICCV51070.2023.01555

Differentiable Transportation Pruning

Yunqiang Li, Jan C. van Gemert, Torsten Hoefler, Bert Moons, Evangelos Eleftheriou, Bram-Ernst Verhoef

Pattern Recognition and Bioinformatics

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

12 Downloads (Pure)

Abstract

Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities.

Original language	English
Title of host publication	Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Editors	Cristina Ceballos
Place of Publication	Piscataway
Publisher	IEEE
Pages	16911-16921
Number of pages	11
ISBN (Electronic)	979-8-3503-0718-4
ISBN (Print)	979-8-3503-0719-1
DOIs	https://doi.org/10.1109/ICCV51070.2023.01555
Publication status	Published - 2023
Event	2023 IEEE/CVF International Conference on Computer Vision (ICCV) - Paris, France Duration: 1 Oct 2023 → 6 Oct 2023

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
ISSN (Print)	1550-5499

Conference

Conference	2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Country/Territory	France
City	Paris
Period	1/10/23 → 6/10/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1109/ICCV51070.2023.01555

Differentiable_Transportation_PruningFinal published version, 1.88 MB

Cite this

Li, Y., van Gemert, J. C., Hoefler, T., Moons, B., Eleftheriou, E., & Verhoef, B.-E. (2023). Differentiable Transportation Pruning. In C. Ceballos (Ed.), Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 16911-16921). (Proceedings of the IEEE International Conference on Computer Vision). IEEE. https://doi.org/10.1109/ICCV51070.2023.01555

@inproceedings{223db2c3485e4eff8a38d97ab41fc3ff,

title = "Differentiable Transportation Pruning",

abstract = "Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities.",

author = "Yunqiang Li and {van Gemert}, {Jan C.} and Torsten Hoefler and Bert Moons and Evangelos Eleftheriou and Bram-Ernst Verhoef",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 2023 IEEE/CVF International Conference on Computer Vision (ICCV) ; Conference date: 01-10-2023 Through 06-10-2023",

year = "2023",

doi = "10.1109/ICCV51070.2023.01555",

language = "English",

isbn = "979-8-3503-0719-1",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "IEEE",

pages = "16911--16921",

editor = "Ceballos, {Cristina }",

booktitle = "Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV)",

address = "United States",

}

Li, Y, van Gemert, JC, Hoefler, T, Moons, B, Eleftheriou, E & Verhoef, B-E 2023, Differentiable Transportation Pruning. in C Ceballos (ed.), Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Proceedings of the IEEE International Conference on Computer Vision, IEEE, Piscataway, pp. 16911-16921, 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 1/10/23. https://doi.org/10.1109/ICCV51070.2023.01555

Differentiable Transportation Pruning. / Li, Yunqiang; van Gemert, Jan C.; Hoefler, Torsten et al.
Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV). ed. / Cristina Ceballos. Piscataway: IEEE, 2023. p. 16911-16921 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Differentiable Transportation Pruning

AU - Li, Yunqiang

AU - van Gemert, Jan C.

AU - Hoefler, Torsten

AU - Moons, Bert

AU - Eleftheriou, Evangelos

AU - Verhoef, Bram-Ernst

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities.

AB - Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities.

UR - http://www.scopus.com/inward/record.url?scp=85183452325&partnerID=8YFLogxK

U2 - 10.1109/ICCV51070.2023.01555

DO - 10.1109/ICCV51070.2023.01555

M3 - Conference contribution

SN - 979-8-3503-0719-1

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 16911

EP - 16921

BT - Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV)

A2 - Ceballos, Cristina

PB - IEEE

CY - Piscataway

T2 - 2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Y2 - 1 October 2023 through 6 October 2023

ER -

Differentiable Transportation Pruning

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this