One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909599608602624 |
|---|---|
| author | Betello, Filippo Purificato, Antonio Vineis, Vittoria Tolomei, Gabriele Silvestri, Fabrizio |
| author_facet | Betello, Filippo Purificato, Antonio Vineis, Vittoria Tolomei, Gabriele Silvestri, Fabrizio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01468 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection Betello, Filippo Purificato, Antonio Vineis, Vittoria Tolomei, Gabriele Silvestri, Fabrizio Artificial Intelligence 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. |
| title | One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.01468 |