高效可变尺寸的神经架构搜索，提升医学图像模型性能与资源适应性。
ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm
- 用零阶近似加速梯度计算，降低搜索开销。
- 在医疗影像数据集上准确率提升1.8%，搜索时间缩短38.6%。
- 支持参数量减少35%以上，适合资源受限场景。
可微分神经架构搜索（NAS）为自动化深度学习模型设计提供了有效路径。然而，现有方法常受限于效率、操作选择及资源约束下的适应性。本文提出ZO-DARTS++，通过零阶近似实现高效梯度处理，引入带温度退火的sparsemax函数以获得更清晰的架构分布，并采用可变尺寸搜索策略生成紧凑且高精度的模型。在多个医学影像数据集上的实验表明，该方法相较标准DARTS平均准确率提升1.8%，搜索时间缩短约38.6%。其资源受限版本可在参数量减少超35%的同时保持竞争力。因此，ZO-DARTS++为实际医疗应用中的高质量、资源感知型深度学习模型生成提供了高效灵活的框架。
原文摘要 · Abstract (English)
Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS methods often face constraints in efficiency, operation selection, and adaptability under varying resource limitations. We introduce ZO-DARTS++, a novel NAS method that effectively balances performance and resource constraints. By integrating a zeroth-order approximation for efficient gradient handling, employing a sparsemax function with temperature annealing for clearer and more interpretable architecture distributions, and adopting a size-variable search scheme for generating compact yet accurate architectures, ZO-DARTS++ establishes a new balance between model complexity and performance. In extensive tests on medical imaging datasets, ZO-DARTS++ improves the average accuracy by up to 1.8\% over standard DARTS-based methods and shortens search time by approximately 38.6\%. Additionally, its resource-constrained variants can reduce the number of parameters by more than 35\% while maintaining competitive accuracy levels. Thus, ZO-DARTS++ offers a versatile and efficient framework for generating high-quality, resource-aware DL models suitable for real-world medical applications.
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。