Performance is not All You Need: Sustainability Considerations for Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiang, Zhang, Chong, Wang, Hongpeng, Gowda, Shreyank Narayana, Li, Yushi, Jin, Xiaobo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908516522917888
author Li, Xiang
Zhang, Chong
Wang, Hongpeng
Gowda, Shreyank Narayana
Li, Yushi
Jin, Xiaobo
author_facet Li, Xiang
Zhang, Chong
Wang, Hongpeng
Gowda, Shreyank Narayana
Li, Yushi
Jin, Xiaobo
contents This work focuses on the high carbon emissions generated by deep learning model training, specifically addressing the core challenge of balancing algorithm performance and energy consumption. It proposes an innovative two-dimensional sustainability evaluation system. Different from the traditional single performance-oriented evaluation paradigm, this study pioneered two quantitative indicators that integrate energy efficiency ratio and accuracy: the sustainable harmonic mean (FMS) integrates accumulated energy consumption and performance parameters through the harmonic mean to reveal the algorithm performance under unit energy consumption; the area under the sustainability curve (ASC) constructs a performance-power consumption curve to characterize the energy efficiency characteristics of the algorithm throughout the cycle. To verify the universality of the indicator system, the study constructed benchmarks in various multimodal tasks, including image classification, segmentation, pose estimation, and batch and online learning. Experiments demonstrate that the system can provide a quantitative basis for evaluating cross-task algorithms and promote the transition of green AI research from theory to practice. Our sustainability evaluation framework code can be found here, providing methodological support for the industry to establish algorithm energy efficiency standards.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00045
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Performance is not All You Need: Sustainability Considerations for Algorithms
Li, Xiang
Zhang, Chong
Wang, Hongpeng
Gowda, Shreyank Narayana
Li, Yushi
Jin, Xiaobo
Computer Vision and Pattern Recognition
Performance
This work focuses on the high carbon emissions generated by deep learning model training, specifically addressing the core challenge of balancing algorithm performance and energy consumption. It proposes an innovative two-dimensional sustainability evaluation system. Different from the traditional single performance-oriented evaluation paradigm, this study pioneered two quantitative indicators that integrate energy efficiency ratio and accuracy: the sustainable harmonic mean (FMS) integrates accumulated energy consumption and performance parameters through the harmonic mean to reveal the algorithm performance under unit energy consumption; the area under the sustainability curve (ASC) constructs a performance-power consumption curve to characterize the energy efficiency characteristics of the algorithm throughout the cycle. To verify the universality of the indicator system, the study constructed benchmarks in various multimodal tasks, including image classification, segmentation, pose estimation, and batch and online learning. Experiments demonstrate that the system can provide a quantitative basis for evaluating cross-task algorithms and promote the transition of green AI research from theory to practice. Our sustainability evaluation framework code can be found here, providing methodological support for the industry to establish algorithm energy efficiency standards.
title Performance is not All You Need: Sustainability Considerations for Algorithms
topic Computer Vision and Pattern Recognition
Performance
url https://arxiv.org/abs/2509.00045