Score: 0

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

Published: May 2, 2025 | arXiv ID: 2505.01468v1

By: Filippo Betello , Antonio Purificato , Vittoria Vineis and more

Potential Business Impact:

Finds smart computer brains that use less power.

Business Areas:
Energy Efficiency Energy, Sustainability

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.

Country of Origin
🇮🇹 Italy

Page Count
27 pages

Category
Computer Science:
Artificial Intelligence