一键选出性能与能耗双赢的AI模型配置。
One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection
- 基于1767次实验构建能耗数据集，动态预测模型表现
- 在多领域任务中实现性能与能耗的帕累托最优
- 适合关注绿色AI、部署优化的研究者和工程师
人工智能的环境影响日益成为全球关注的问题，尤其体现在模型训练阶段。本文提出GREEN（面向能效网络的引导推荐），一种新的推理时方法，可跨不同人工智能领域和任务，推荐在验证性能与能耗之间达到帕累托最优的模型配置。该方法克服了现有能效神经架构搜索方法通常局限于特定架构或任务的局限性。核心在于EcoTaskSet数据集，包含来自计算机视觉、自然语言处理和推荐系统领域的1767次实验的训练动态，涵盖广泛使用及前沿架构。利用该数据集与预测模型，本方法可根据用户偏好有效选择最优模型配置。实验表明，该方法在保持竞争力性能的同时，成功识别出节能型模型配置。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。