用集成方法精准预测模型性能，省去训练时间。
GreenFactory: Ensembling Zero-Cost Proxies to Estimate Performance of Neural Networks
- 集成多个零成本代理指标，用随机森林回归预测准确率。
- 在NATS-Bench上对三类数据集的预测相关性超0.9，效果稳定。
- 适合需要快速筛选神经网络架构的研究者使用。
在神经网络架构搜索中，评估模型性能对找到最优架构和超参数至关重要。传统方法需训练并评估每个网络，耗时且资源消耗大。零成本代理可在不训练的情况下估计性能，但现有方法泛化能力弱，仅提供相对排名而非准确率预测。为此，我们提出GreenFactory，一个零成本代理的集成方法，利用随机森林回归器融合多个预测器的优势，直接预测模型测试准确率。我们在NATS-Bench上进行了评估，结果稳健：在NATS-Bench-SSS上，对CIFAR-10、CIFAR-100和ImageNet-16-120的肯德尔相关系数分别为0.907、0.945和0.920；在NATS-Bench-TSS上，对应值为0.921、0.929和0.908，表明其在不同搜索空间中均具高度可靠性。
原文摘要 · Abstract (English)
Determining the performance of a Deep Neural Network during Neural Architecture Search processes is essential for identifying optimal architectures and hyperparameters. Traditionally, this process requires training and evaluation of each network, which is time-consuming and resource-intensive. Zero-cost proxies estimate performance without training, serving as an alternative to traditional training. However, recent proxies often lack generalization across diverse scenarios and provide only relative rankings rather than predicted accuracies. To address these limitations, we propose GreenFactory, an ensemble of zero-cost proxies that leverages a random forest regressor to combine multiple predictors' strengths and directly predict model test accuracy. We evaluate GreenFactory on NATS-Bench, achieving robust results across multiple datasets. Specifically, GreenFactory achieves high Kendall correlations on NATS-Bench-SSS, indicating substantial agreement between its predicted scores and actual performance: 0.907 for CIFAR-10, 0.945 for CIFAR-100, and 0.920 for ImageNet-16-120. Similarly, on NATS-Bench-TSS, we achieve correlations of 0.921 for CIFAR-10, 0.929 for CIFAR-100, and 0.908 for ImageNet-16-120, showcasing its reliability in both search spaces.
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。