Data Proxy Generation for Fast and Efficient Neural Architecture Search
This addresses efficiency issues for researchers and practitioners using NAS on large-scale datasets, though it is incremental as it builds on existing NAS methods.
The paper tackles the high computational cost of Neural Architecture Search (NAS) by proposing a method to create a data proxy that reduces dataset size by 10-20× while preserving relative accuracy rankings between network configurations.
Due to the recent advances on Neural Architecture Search (NAS), it gains popularity in designing best networks for specific tasks. Although it shows promising results on many benchmarks and competitions, NAS still suffers from its demanding computation cost for searching high dimensional architectural design space, and this problem becomes even worse when we want to use a large-scale dataset. If we can make a reliable data proxy for NAS, the efficiency of NAS approaches increase accordingly. Our basic observation for making a data proxy is that each example in a specific dataset has a different impact on NAS process and most of examples are redundant from a relative accuracy ranking perspective, which we should preserve when making a data proxy. We propose a systematic approach to measure the importance of each example from this relative accuracy ranking point of view, and make a reliable data proxy based on the statistics of training and testing examples. Our experiment shows that we can preserve the almost same relative accuracy ranking between all possible network configurations even with 10-20$\times$ smaller data proxy.