arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.15232cs.LGcs.AIcs.CVstat.ML
收藏

用于神经结构搜索的引导进化

Guided Evolution for Neural Architecture Search

NOVA LINCS;Universidade da Beira Interior(贝拉内陆大学)

Vasco Lopes, Miguel Santos, Bruno Degardin, Luís A. Alexandre

摘要:

神经结构搜索(NAS)方法已成功地应用于图像任务,取得了良好的效果。然而,NAS方法通常是复杂的,并且一旦生成的架构似乎产生良好的结果,就倾向于收敛到局部最小值。在本文中,我们提出了G-EA,一种新的指导进化NAS的方法。G-EA背后的基本原理是通过在初始化阶段使用零代理估计器在每一代中生成和评估几个架构来探索搜索空间,其中只有最高得分的网络被训练并保留用于下一代。在初始化阶段的这种评估允许在不增加计算的情况下从搜索空间连续提取知识,从而允许有效地引导搜索。此外,G-EA迫使后代利用性能最好的网络,同时迫使父母突变和有利于年轻的架构,以损害老年人的探索。实验结果表明,G-EA在NAS-Bench-201搜索空间中,在CIFAR-10、CIFAR-100和ImageNet16 - 120上的平均准确率分别为93.98%、72.12%和45.94%。

英文摘要:

Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures seem to yield good results. In this paper, we propose G-EA, a novel approach for guided evolutionary NAS. The rationale behind G-EA, is to explore the search space by generating and evaluating several architectures in each generation at initialization stage using a zero-proxy estimator, where only the highest-scoring network is trained and kept for the next generation. This evaluation at initialization stage allows continuous extraction of knowledge from the search space without increasing computation, thus allowing the search to be efficiently guided. Moreover, G-EA forces exploitation of the most performant networks by descendant generation while at the same time forcing exploration by parent mutation and by favouring younger architectures to the detriment of older ones. Experimental results demonstrate the effectiveness of the proposed method, showing that G-EA achieves state-of-the-art results in NAS-Bench-201 search space in CIFAR-10, CIFAR-100 and ImageNet16-120, with mean accuracies of 93.98%, 72.12% and 45.94% respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑