NAS-Bench-x11 and the Power of Learning Curves
This work addresses a bottleneck for NAS researchers by enabling more efficient and reproducible multi-fidelity methods, though it is incremental as it builds on existing benchmark frameworks.
The authors tackled the limitation of existing neural architecture search (NAS) benchmarks by creating surrogate benchmarks (NAS-Bench-111, NAS-Bench-311, NAS-Bench-NLP11) that provide full training information, enabling multi-fidelity techniques like learning curve extrapolation, which improved over state-of-the-art single-fidelity algorithms.
While early research in neural architecture search (NAS) required extreme computational resources, the recent releases of tabular and surrogate benchmarks have greatly increased the speed and reproducibility of NAS research. However, two of the most popular benchmarks do not provide the full training information for each architecture. As a result, on these benchmarks it is not possible to run many types of multi-fidelity techniques, such as learning curve extrapolation, that require evaluating architectures at arbitrary epochs. In this work, we present a method using singular value decomposition and noise modeling to create surrogate benchmarks, NAS-Bench-111, NAS-Bench-311, and NAS-Bench-NLP11, that output the full training information for each architecture, rather than just the final validation accuracy. We demonstrate the power of using the full training information by introducing a learning curve extrapolation framework to modify single-fidelity algorithms, showing that it leads to improvements over popular single-fidelity algorithms which claimed to be state-of-the-art upon release. Our code and pretrained models are available at https://github.com/automl/nas-bench-x11.