EmProx: Neural Network Performance Estimation For Neural Architecture Search
This work addresses the efficiency bottleneck in neural architecture search for researchers and practitioners, though it is incremental as it builds on prior embedding-based approaches.
The paper tackles the problem of reducing search time in Neural Architecture Search by proposing EmProx Score, a method that estimates neural network performance using embedding proximity, achieving accuracy comparable to existing methods while being up to 80 times faster.
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.