$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
This addresses stability and generalization problems in neural architecture search for researchers and practitioners, but it is incremental as it builds on existing DARTS methods.
The paper tackles the issues of weak robustness to performance collapse and poor generalization in differentiable architecture search (DARTS) by proposing Beta-Decay regularization, which stabilizes the search process and improves transferability across datasets, as validated on NAS-Bench-201 and other benchmarks.
Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficiency. However, they suffer from two main issues, the weak robustness to the performance collapse and the poor generalization ability of the searched architectures. To solve these two problems, a simple-but-efficient regularization method, termed as Beta-Decay, is proposed to regularize the DARTS-based NAS searching process. Specifically, Beta-Decay regularization can impose constraints to keep the value and variance of activated architecture parameters from too large. Furthermore, we provide in-depth theoretical analysis on how it works and why it works. Experimental results on NAS-Bench-201 show that our proposed method can help to stabilize the searching process and makes the searched network more transferable across different datasets. In addition, our search scheme shows an outstanding property of being less dependent on training time and data. Comprehensive experiments on a variety of search spaces and datasets validate the effectiveness of the proposed method.