Speeding up NAS with Adaptive Subset Selection
This work addresses the efficiency bottleneck in NAS for researchers and practitioners, though it is incremental as it builds on existing methods.
The paper tackles the high computational cost of neural architecture search (NAS) by introducing an adaptive subset selection approach that reduces runtime without sacrificing accuracy, achieving consistent speedups across multiple datasets and algorithms like DARTS-PT, BOHB, and DEHB.
A majority of recent developments in neural architecture search (NAS) have been aimed at decreasing the computational cost of various techniques without affecting their final performance. Towards this goal, several low-fidelity and performance prediction methods have been considered, including those that train only on subsets of the training data. In this work, we present an adaptive subset selection approach to NAS and present it as complementary to state-of-the-art NAS approaches. We uncover a natural connection between one-shot NAS algorithms and adaptive subset selection and devise an algorithm that makes use of state-of-the-art techniques from both areas. We use these techniques to substantially reduce the runtime of DARTS-PT (a leading one-shot NAS algorithm), as well as BOHB and DEHB (leading multifidelity optimization algorithms), without sacrificing accuracy. Our results are consistent across multiple datasets, and towards full reproducibility, we release our code at https: //anonymous.4open.science/r/SubsetSelection NAS-B132.