Energy consumption from the selection, training, and deployment of deep learning models has seen a significant uptick recently. This work aims to facilitate the design of energy-efficient deep learning models that require less computational resources and prioritize environmental sustainability by focusing on the energy consumption. Neural architecture search (NAS) benefits from tabular benchmarks, which evaluate NAS strategies cost-effectively through precomputed performance statistics. We advocate for including energy efficiency as an additional performance criterion in NAS. To this end, we introduce an enhanced tabular benchmark encompassing data on energy consumption for varied architectures. The benchmark, designated as EC-NAS, has been made available in an open-source format to advance research in energy-conscious NAS. EC-NAS incorporates a surrogate model to predict energy consumption, aiding in diminishing the energy expenditure of the dataset creation. Our findings emphasize the potential of EC-NAS by leveraging multi-objective optimization algorithms, revealing a balance between energy usage and accuracy. This suggests the feasibility of identifying energy-lean architectures with little or no compromise in performance.

翻译：近年来，深度学习模型的选择、训练和部署所消耗的能源显著增加。本研究旨在通过关注能耗问题，推动设计所需计算资源较少、且优先考虑环境可持续性的节能深度学习模型。神经架构搜索（NAS）得益于表格基准，这些基准通过预先计算的性能统计数据，以低成本效益的方式评估NAS策略。我们主张将能效作为NAS中的额外性能标准纳入考量。为此，我们引入了一个增强型表格基准，其中涵盖不同架构的能耗数据。该基准被命名为EC-NAS，并以开源形式发布，以推动能耗感知NAS研究的发展。EC-NAS包含一个用于预测能耗的代理模型，有助于减少数据集创建过程中的能源消耗。我们的研究结果强调了EC-NAS的潜力，通过利用多目标优化算法，揭示了能耗与准确率之间的平衡。这表明，在几乎不损失性能甚至无性能损失的情况下识别出低能耗架构是可行的。