Reducing neural architecture search spaces with training-free statistics and computational graph clustering
ACM International Conference on Computing Frontiers (CF)(2022)
摘要
The computational demands of neural architecture search (NAS) algorithms are usually directly proportional to the size of their target search spaces. Thus, limiting the search to high-quality subsets can greatly reduce the computational load of NAS algorithms. In this paper, we present Clustering-Based REDuction (C-BRED), a new technique to reduce the size of NAS search spaces. C-BRED reduces a NAS space by clustering the computational graphs associated with its architectures and selecting the most promising cluster using proxy statistics correlated with network accuracy. When considering the NAS-Bench-201 (NB201) data set and the CIFAR-100 task, C-BRED selects a subset with 70% average accuracy instead of the whole space's 64% average accuracy.
更多查看译文
关键词
deep learning, neural architecture search, training-free statistics, computational graph, clustering
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要