论文标题
Emprox：神经架构搜索的神经网络绩效估计
EmProx: Neural Network Performance Estimation For Neural Architecture Search
论文作者
论文摘要
常见的神经体系结构搜索方法生成了大量需要培训以评估其性能并找到最佳体系结构的候选架构。为了最大程度地减少搜索时间，我们使用不同的性能估计策略。此类策略的有效性在准确性，适合和查询时间方面有所不同。这项研究提出了一种新方法，即Emprox评分（嵌入接近得分）。与神经体系结构优化（NAO）类似，此方法将候选体系结构映射到使用编码器解码器框架的连续嵌入空间。然后，使用加权KNN估算候选者的性能，该构建体的嵌入向量已知。该方法的性能估计与NAO中使用的MLP性能预测指标相当，而与NAO相比，训练的速度快了近9倍。目前使用的其他绩效估算策略的基准测试表现出类似于更好的准确性，而五十倍的速度也快五十倍。
Common Neural Architecture Search methods generate large amounts of candidate architectures that need training in order to assess their performance and find an optimal architecture. To minimize the search time we use different performance estimation strategies. The effectiveness of such strategies varies in terms of accuracy and fit and query time. This study proposes a new method, EmProx Score (Embedding Proximity Score). Similar to Neural Architecture Optimization (NAO), this method maps candidate architectures to a continuous embedding space using an encoder-decoder framework. The performance of candidates is then estimated using weighted kNN based on the embedding vectors of architectures of which the performance is known. Performance estimations of this method are comparable to the MLP performance predictor used in NAO in terms of accuracy, while being nearly nine times faster to train compared to NAO. Benchmarking against other performance estimation strategies currently used shows similar to better accuracy, while being five up to eighty times faster.
