mlsanityData to 14 Oct 2026

One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection

arXiv 2505.01468 ↗First posted 2 May 2025cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The environmental impact of Artificial Intelligence (AI) is emerging as a significant global concern, particularly regarding model training. In this paper, we introduce GREEN (Guided Recommendations of Energy-Efficient Networks), a novel, inference-time approach for recommending Pareto-optimal AI model configurations that optimize validation performance and energy consumption across diverse AI domains and tasks. Our approach directly addresses the limitations of current eco-efficient neural architecture search methods, which are often restricted to specific architectures or tasks. Central to this work is EcoTaskSet, a dataset comprising training dynamics from over 1767 experiments across computer vision, natural language processing, and recommendation systems using both widely used and cutting-edge architectures. Leveraging this dataset and a prediction model, our approach demonstrates effectiveness in selecting the best model configuration based on user preferences. Experimental results show that our method successfully identifies energy-efficient configurations while ensuring competitive performance.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 2 May 2025.

Builds on

32 of 54 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  9. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  10. 2018Self-Attentive Sequential Recommendationcited by 1,184
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  12. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
20 more
  1. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  2. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  3. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  4. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  5. 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 153
  6. 2013A Theoretical Analysis of NDCG Type Ranking Measurescited by 119
  7. 2022Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Trainingcited by 79
  8. 2023LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Modelscited by 72
  9. 2020Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDLcited by 67
  10. 2020Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarkscited by 67
  11. 2022CORE: Simple and Effective Session-based Recommendation within Consistent Representation Spacecited by 37
  12. 2020Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Searchcited by 33
  13. 2021KNAS: Green Neural Architecture Searchcited by 33
  14. 2020Using a thousand optimization tasks to learn hyperparameter search strategiescited by 29
  15. 2023Reducing Energy Bloat in Large Model Trainingcited by 22
  16. 2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
  17. 2022EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Searchcited by 11
  18. 2024From Clicks to Carbon: The Environmental Toll of Recommender Systemscited by 11
  19. 2024CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Frameworkcited by 5
  20. 2024A Reproducible Analysis of Sequential Recommender Systemscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUscited by 3