提出可精确优化图结构搜索空间的方法，提升神经网络架构搜索效率。
Global optimization of graph acquisition functions for neural architecture search
- 构建图输入空间的显式优化公式，支持可达性与最短路径约束
- 在多个NAS基准上高效找到最优架构，验证方法有效性
- 适合追求高数据效率的架构搜索研究者
图贝叶斯优化（Graph BO）作为神经网络架构搜索（NAS）中一种强大且数据高效的工具展现出潜力。现有工作多聚焦于图代理模型的设计，如网络度量和核函数以量化网络间相似性，但针对图结构的离散优化任务——即获取函数优化——因图搜索空间与获取函数建模复杂而研究不足。本文提出图输入空间的显式优化形式，包含可达性、最短路径等性质，并用于后续图核与获取函数构建。理论证明所提编码为图空间的等价表示，同时给出节点或边带标签的NAS领域限制条件。在多个NAS基准上的数值结果表明，该方法在多数情况下能高效找到最优架构，凸显其有效性。
原文摘要 · Abstract (English)
Graph Bayesian optimization (BO) has shown potential as a powerful and data-efficient tool for neural architecture search (NAS). Most existing graph BO works focus on developing graph surrogates models, i.e., metrics of networks and/or different kernels to quantify the similarity between networks. However, the acquisition optimization, as a discrete optimization task over graph structures, is not well studied due to the complexity of formulating the graph search space and acquisition functions. This paper presents explicit optimization formulations for graph input space including properties such as reachability and shortest paths, which are used later to formulate graph kernels and the acquisition function. We theoretically prove that the proposed encoding is an equivalent representation of the graph space and provide restrictions for the NAS domain with either node or edge labels. Numerical results over several NAS benchmarks show that our method efficiently finds the optimal architecture for most cases, highlighting its efficacy.
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。