发表机构
Bosch Center for Artificial Intelligence; LMU Munich; Munich Center for Machine Learning (MCML)（博世人工智能中心; 慕尼黑大学; 慕尼黑机器学习中心（MCML））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出PPNAS，一种预测驱动的神经架构搜索方法，通过融合少量真实性能标签与大量零成本代理信息，利用序数信息构建成对排序监督并去偏，在有限评估预算下实现最先进性能。
AI 中文摘要
在神经架构搜索（NAS）中评估候选架构面临一个固有的权衡：一方面，可靠的性能标签是有限的，因为训练和评估架构成本高昂；另一方面，零成本代理（ZCPs）在大规模计算时成本低廉，但可能带有噪声。然而，如何有效地结合这两种监督来源仍不清楚。在本文中，我们提出了PPNAS，一种新颖的预测驱动推理（PPI）方法用于NAS。PPNAS融合了（1）一小部分具有观测性能标签的架构和（2）大量具有ZCP信息的架构。为了结合这两种监督来源，PPNAS利用ZCP提供的序数信息来构建额外的成对排序监督，而PPI则对基于ZCP的排序与真实性能排序之间的系统性差异进行去偏。我们在端到端的基于预测器的NAS中评估了PPNAS，在有限的评估预算下达到了最先进的性能。据我们所知，PPNAS是首个用于标签高效NAS的预测驱动方法。
英文摘要
Evaluating candidate architectures in neural architecture search (NAS) faces an inherent trade-off: on the one hand, reliable performance labels are limited because training and evaluating architectures is costly; on the other hand, zero-cost proxies (ZCPs) are cheap to compute at large scale but can be noisy. Yet, how to effectively combine these two sources of supervision remains unclear. In this paper, we propose PPNAS, a novel prediction-powered inference (PPI) approach for NAS. PPNAS fuses (1) a small set of architectures with observed performance labels and (2) a large set of architectures with ZCP information. To combine these two sources of supervision, PPNAS exploits the ordinal information provided by ZCPs to construct additional pairwise ranking supervision, while PPI debiases systematic discrepancies between ZCP-based and true performance rankings. We evaluate PPNAS in end-to-end predictor-based NAS, where it achieves state-of-the-art under limited evaluation budgets. To the best of our knowledge, PPNAS is the first prediction-powered approach for label-efficient NAS.
