arXiv · 2112.02488
Exploring Complicated Search Spaces with Interleaving-Free Sampling
Abstract
The existing neural architecture search algorithms are mostly working on search spaces with short-distance connections. We argue that such designs, though safe and stable, obstacles the search algorithms from exploring more complicated scenarios. In this paper, we build the search algorithm upon a complicated search space with long-distance connections, and show that existing weight-sharing search algorithms mostly fail due to the existence of \textbf{interleaved connections}. Based on the observation, we present a simple yet effective algorithm named \textbf{IF-NAS}, where we perform a periodic sampling strategy to construct different sub-networks during the search procedure, avoiding the interleaved connections to emerge in any of them. In the proposed search space, IF-NAS outperform both random sampling and previous weight-sharing search algorithms by a significant margin. IF-NAS also generalizes to the micro cell-based spaces which are much easier. Our research emphasizes the importance of macro structure and we look forward to further efforts along this direction.
Explore related subjects
Keep this discovery
Yunjie Tian, Lingxi Xie, Jiemin Fang, Jianbin Jiao, Qixiang Ye, Qi Tian. 2021-12-05. Exploring Complicated Search Spaces with Interleaving-Free Sampling. https://arxiv.org/abs/2112.02488
Cite the original work for its findings. Save a collection to share your selection of sources.