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，深度学习模型的选型、训练和部署所产生的能耗显著增加。本研究通过聚焦能耗问题，旨在促进设计能耗高效、计算资源需求低且优先考虑环境可持续性的深度学习模型。神经架构搜索（NAS）得益于表格基准，这些基准通过预计算的性能统计数据，以高性价比的方式评估NAS策略。我们主张将能耗效率作为附加性能指标纳入NAS。为此，我们引入了一个增强型表格基准，该基准涵盖了不同架构的能耗数据。该基准名为EC-NAS，已以开源形式发布，以推动节能型NAS的研究发展。EC-NAS集成了一个用于预测能耗的代理模型，有助于降低数据集创建过程中的能源消耗。我们的研究结果通过利用多目标优化算法，凸显了EC-NAS的潜力，揭示了能耗与准确率之间的平衡。这表明，在性能几乎不受损或完全不受损的情况下，识别出低能耗架构是可行的。