GreenAuto自动设计节能AI模型，适配边缘设备。
GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices
- 基于帕累托前沿的自动化搜索，结合梯度优化探索模型空间
- 用预训练能量预测器估算能耗，指导高效可持续模型发现
- 全流程自动化，无需人工干预，适合边缘计算场景
我们提出GreenAuto，一个端到端的自动化平台，用于可持续AI模型的设计、生成、部署与评估。GreenAuto在扩展的神经架构搜索（NAS）空间中采用基于帕累托前沿的搜索方法，并通过梯度下降优化模型探索过程。利用预训练的核级能量预测器，对所有候选模型进行能耗估算，提供全局视角以引导搜索向更可持续的方向发展。通过自动化性能测量并迭代优化搜索流程，GreenAuto实现了无需人工干预的高效可持续模型识别。
原文摘要 · Abstract (English)
We present GreenAuto, an end-to-end automated platform designed for sustainable AI model exploration, generation, deployment, and evaluation. GreenAuto employs a Pareto front-based search method within an expanded neural architecture search (NAS) space, guided by gradient descent to optimize model exploration. Pre-trained kernel-level energy predictors estimate energy consumption across all models, providing a global view that directs the search toward more sustainable solutions. By automating performance measurements and iteratively refining the search process, GreenAuto demonstrates the efficient identification of sustainable AI models without the need for human intervention.
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。