Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub

Taewon Yoo; Hyunmin Lee; Seung Young Oh; Hyosun Kwon; Hyunggu Jung

doi:10.1145/3584931.3606959

Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub

Taewon Yoo, Hyunmin Lee, Seung Young Oh, Hyosun Kwon, Hyunggu Jung

Department of Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The increasing performance of machine learning (ML) models necessitates greater computing resources, contributing to rising carbon intensity in ML computing and raising concerns about computational equity. Previous studies focused on developing tools that enable model developers to view the carbon intensity of the ML models in the training process. Still, little is known about how to support ML developers in online communities to explore the carbon intensity of ML models during inference. We developed MIEV, a model inference emission visualizer, that supports ML developers on TensorFlow Hub to explore the carbon intensity of image domain models during the model Inference phase. We also provide insights into designing technologies that promote collaborative work among ML developers to drive sustainable AI development processes. To the best of our knowledge, this is the first attempt to interactively visualize the carbon intensity of ML models in online communities during the Inference phase.

Original language	English
Title of host publication	CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing
Editors	Morgan Ames, Susan Fussell, Eric Gilbert, Vera Liao, Xiaojuan Ma, Xinru Page, Mark Rouncefield, Vivek Singh, Pamela Wisniewski
Publisher	Association for Computing Machinery
Pages	206-211
Number of pages	6
ISBN (Electronic)	9798400701290
DOIs	https://doi.org/10.1145/3584931.3606959
State	Published - 14 Oct 2023
Event	26th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2023 - Minneapolis, United States Duration: 14 Oct 2023 → 18 Oct 2023

Publication series

Name	Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW

Conference

Conference	26th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2023
Country/Territory	United States
City	Minneapolis
Period	14/10/23 → 18/10/23

Keywords

TensorFlow Hub
carbon intensity
inference
online communities

Access to Document

10.1145/3584931.3606959

Cite this

Yoo, T., Lee, H., Oh, S. Y., Kwon, H., & Jung, H. (2023). Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub. In M. Ames, S. Fussell, E. Gilbert, V. Liao, X. Ma, X. Page, M. Rouncefield, V. Singh, & P. Wisniewski (Eds.), CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing (pp. 206-211). (Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW). Association for Computing Machinery. https://doi.org/10.1145/3584931.3606959

Yoo, Taewon ; Lee, Hyunmin ; Oh, Seung Young et al. / Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub. CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing. editor / Morgan Ames ; Susan Fussell ; Eric Gilbert ; Vera Liao ; Xiaojuan Ma ; Xinru Page ; Mark Rouncefield ; Vivek Singh ; Pamela Wisniewski. Association for Computing Machinery, 2023. pp. 206-211 (Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW).

@inproceedings{1ac64d4edb2d4baba005398b91d607a4,

title = "Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub",

abstract = "The increasing performance of machine learning (ML) models necessitates greater computing resources, contributing to rising carbon intensity in ML computing and raising concerns about computational equity. Previous studies focused on developing tools that enable model developers to view the carbon intensity of the ML models in the training process. Still, little is known about how to support ML developers in online communities to explore the carbon intensity of ML models during inference. We developed MIEV, a model inference emission visualizer, that supports ML developers on TensorFlow Hub to explore the carbon intensity of image domain models during the model Inference phase. We also provide insights into designing technologies that promote collaborative work among ML developers to drive sustainable AI development processes. To the best of our knowledge, this is the first attempt to interactively visualize the carbon intensity of ML models in online communities during the Inference phase.",

keywords = "TensorFlow Hub, carbon intensity, inference, online communities",

author = "Taewon Yoo and Hyunmin Lee and Oh, {Seung Young} and Hyosun Kwon and Hyunggu Jung",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 26th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2023 ; Conference date: 14-10-2023 Through 18-10-2023",

year = "2023",

month = oct,

day = "14",

doi = "10.1145/3584931.3606959",

language = "English",

series = "Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW",

publisher = "Association for Computing Machinery",

pages = "206--211",

editor = "Morgan Ames and Susan Fussell and Eric Gilbert and Vera Liao and Xiaojuan Ma and Xinru Page and Mark Rouncefield and Vivek Singh and Pamela Wisniewski",

booktitle = "CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing",

}

Yoo, T, Lee, H, Oh, SY, Kwon, H & Jung, H 2023, Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub. in M Ames, S Fussell, E Gilbert, V Liao, X Ma, X Page, M Rouncefield, V Singh & P Wisniewski (eds), CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing. Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW, Association for Computing Machinery, pp. 206-211, 26th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2023, Minneapolis, United States, 14/10/23. https://doi.org/10.1145/3584931.3606959

Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub. / Yoo, Taewon; Lee, Hyunmin; Oh, Seung Young et al.
CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing. ed. / Morgan Ames; Susan Fussell; Eric Gilbert; Vera Liao; Xiaojuan Ma; Xinru Page; Mark Rouncefield; Vivek Singh; Pamela Wisniewski. Association for Computing Machinery, 2023. p. 206-211 (Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub

AU - Yoo, Taewon

AU - Lee, Hyunmin

AU - Oh, Seung Young

AU - Kwon, Hyosun

AU - Jung, Hyunggu

PY - 2023/10/14

Y1 - 2023/10/14

N2 - The increasing performance of machine learning (ML) models necessitates greater computing resources, contributing to rising carbon intensity in ML computing and raising concerns about computational equity. Previous studies focused on developing tools that enable model developers to view the carbon intensity of the ML models in the training process. Still, little is known about how to support ML developers in online communities to explore the carbon intensity of ML models during inference. We developed MIEV, a model inference emission visualizer, that supports ML developers on TensorFlow Hub to explore the carbon intensity of image domain models during the model Inference phase. We also provide insights into designing technologies that promote collaborative work among ML developers to drive sustainable AI development processes. To the best of our knowledge, this is the first attempt to interactively visualize the carbon intensity of ML models in online communities during the Inference phase.

AB - The increasing performance of machine learning (ML) models necessitates greater computing resources, contributing to rising carbon intensity in ML computing and raising concerns about computational equity. Previous studies focused on developing tools that enable model developers to view the carbon intensity of the ML models in the training process. Still, little is known about how to support ML developers in online communities to explore the carbon intensity of ML models during inference. We developed MIEV, a model inference emission visualizer, that supports ML developers on TensorFlow Hub to explore the carbon intensity of image domain models during the model Inference phase. We also provide insights into designing technologies that promote collaborative work among ML developers to drive sustainable AI development processes. To the best of our knowledge, this is the first attempt to interactively visualize the carbon intensity of ML models in online communities during the Inference phase.

KW - TensorFlow Hub

KW - carbon intensity

KW - inference

KW - online communities

UR - http://www.scopus.com/inward/record.url?scp=85176271792&partnerID=8YFLogxK

U2 - 10.1145/3584931.3606959

DO - 10.1145/3584931.3606959

M3 - Conference contribution

AN - SCOPUS:85176271792

T3 - Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW

SP - 206

EP - 211

BT - CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing

A2 - Ames, Morgan

A2 - Fussell, Susan

A2 - Gilbert, Eric

A2 - Liao, Vera

A2 - Ma, Xiaojuan

A2 - Page, Xinru

A2 - Rouncefield, Mark

A2 - Singh, Vivek

A2 - Wisniewski, Pamela

PB - Association for Computing Machinery

T2 - 26th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2023

Y2 - 14 October 2023 through 18 October 2023

ER -

Yoo T, Lee H, Oh SY, Kwon H, Jung H. Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub. In Ames M, Fussell S, Gilbert E, Liao V, Ma X, Page X, Rouncefield M, Singh V, Wisniewski P, editors, CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery. 2023. p. 206-211. (Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW). doi: 10.1145/3584931.3606959

Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow Hub

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this