Network Graph Based Neural Architecture Search
This work addresses the computational cost and lack of insight in neural architecture search for machine learning researchers, though it appears incremental as it builds on existing search methods with a graph-based twist.
The authors tackled the problem of computationally expensive and non-intuitive neural architecture search by proposing a graph-based method that predicts architecture performance using graph properties, achieving remarkably efficient search and identifying effective graph properties for performance prediction.
Neural architecture search enables automation of architecture design. Despite its success, it is computationally costly and does not provide an insight on how to design a desirable architecture. Here we propose a new way of searching neural network where we search neural architecture by rewiring the corresponding graph and predict the architecture performance by graph properties. Because we do not perform machine learning over the entire graph space and use predicted architecture performance to search architecture, the searching process is remarkably efficient. We find graph based search can give a reasonably good prediction of desirable architecture. In addition, we find graph properties that are effective to predict architecture performance. Our work proposes a new way of searching neural architecture and provides insights on neural architecture design.