论文标题
B2EA：由两个用于神经建筑搜索的贝叶斯优化模块辅助的进化算法
B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture Search
论文作者
论文摘要
早期开创性的神经体系结构搜索（NAS）作品是适用于任何一般搜索空间的多试方法。随后的作品利用了早期发现，并开发了体重共享方法，这些方法通常使用结构化的搜索空间，通常具有预固定的超参数。尽管重量共享NAS算法具有惊人的计算效率，但很明显，还需要进行多个试验的NAS算法来识别非常高性能的体系结构，尤其是在探索一般搜索空间时。在这项工作中，我们仔细审查了最新的多试NAS算法，并确定包括进化算法（EA），贝叶斯优化（BO），多元化，输入和输出转换以及降低保真度估计的关键策略。为了将关键策略适应一个单一的框架，我们开发了B2EA，它是替代辅助EA，通过两个BO替代模型和两者之间的突变步骤。为了证明B2EA是强大而有效的，我们评估了14个基准和基于细胞的搜索空间的三个性能指标。与最先进的多试算法的比较表明，对于三个难度级别的目标性能水平，B2EA在14个基准测试中是强大而有效的。 B2EA代码可在\ url {https://github.com/snu-adsl/bbea}上公开获得。
The early pioneering Neural Architecture Search (NAS) works were multi-trial methods applicable to any general search space. The subsequent works took advantage of the early findings and developed weight-sharing methods that assume a structured search space typically with pre-fixed hyperparameters. Despite the amazing computational efficiency of the weight-sharing NAS algorithms, it is becoming apparent that multi-trial NAS algorithms are also needed for identifying very high-performance architectures, especially when exploring a general search space. In this work, we carefully review the latest multi-trial NAS algorithms and identify the key strategies including Evolutionary Algorithm (EA), Bayesian Optimization (BO), diversification, input and output transformations, and lower fidelity estimation. To accommodate the key strategies into a single framework, we develop B2EA that is a surrogate assisted EA with two BO surrogate models and a mutation step in between. To show that B2EA is robust and efficient, we evaluate three performance metrics over 14 benchmarks with general and cell-based search spaces. Comparisons with state-of-the-art multi-trial algorithms reveal that B2EA is robust and efficient over the 14 benchmarks for three difficulty levels of target performance. The B2EA code is publicly available at \url{https://github.com/snu-adsl/BBEA}.
