mlsanityData to 7 Oct 2026

Energy Efficiency of Training Neural Network Architectures: An Empirical Study

arXiv 2302.00967 ↗First posted 2 Feb 2023cs.LG cs.AI cs.SEcited by 15

Not on the map. Why?

Abstract (arXiv)

The evaluation of Deep Learning models has traditionally focused on criteria such as accuracy, F1 score, and related measures. The increasing availability of high computational power environments allows the creation of deeper and more complex models. However, the computations needed to train such models entail a large carbon footprint. In this work, we study the relations between DL model architectures and their environmental impact in terms of energy consumed and CO2 emissions produced during training by means of an empirical study using Deep Convolutional Neural Networks. Concretely, we study: (i) the impact of the architecture and the location where the computations are hosted on the energy consumption and emissions produced; (ii) the trade-off between accuracy and energy efficiency; and (iii) the difference on the method of measurement of the energy consumed using software-based and hardware-based tools.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 2 Feb 2023.

Builds on

13 of 25 references.

References · 13

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  8. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  9. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  10. 2019Green AIcited by 620
  11. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  12. 2021Integration of Convolutional Neural Networks in Mobile Applicationscited by 6
1 more
  1. 2021Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?cited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 5; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023Exploring the Carbon Footprint of Hugging Face's ML Models: A Repository Mining Studycited by 23
  2. 2023A Synthesis of Green Architectural Tactics for ML-Enabled Systemscited by 17
  3. 2024Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructurescited by 11
  4. 2023Towards green AI-based software systems: an architecture-centric approach (GAISSA)cited by 3
  5. 2024How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detectioncited by 3
  6. 2024Impact of ML Optimization Tactics on Greener Pre-Trained ML Modelscited by 2
  7. 2024The More the Merrier? Navigating Accuracy vs. Energy Efficiency Design Trade-Offs in Ensemble Learning Systemscited by 1
  8. 2025Sustainable Machine Learning Retraining: Optimizing Energy Efficiency Without Compromising Accuracycited by 1
  9. 2025EBA-AI: Ethics-Guided Bias-Aware AI for Efficient Underwater Image Enhancement and Coral Reef Monitoringcited by 1
  10. 2025Energy Consumption in Parallel Neural Network Trainingcited by 1
  11. 2024Insights into resource utilization of code small language models serving with runtime engines and execution providerscited by 0
  12. 2025Who Wins the Race? (R Vs Python) - An Exploratory Study on Energy Consumption of Machine Learning Algorithmscited by 0
3 more
  1. 2025Green AI: A systematic review and meta-analysis of its definitions, lifecycle models, hardware and measurement attemptscited by 0
  2. 2026LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systemscited by 0
  3. 2026TextTeacher: What Can Language Teach About Images?cited by 0