One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection
This addresses the problem of reducing AI's environmental footprint for researchers and practitioners, though it is incremental as it builds on existing eco-efficient neural architecture search methods.
The paper tackles the environmental impact of AI model training by introducing GREEN, an inference-time approach that recommends Pareto-optimal model configurations to optimize validation performance and energy consumption across diverse domains, achieving competitive performance with energy-efficient configurations.
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.