LGCVDec 5, 2021

Exploring Complicated Search Spaces with Interleaving-Free Sampling

arXiv:2112.02488v1
Originality Incremental advance
AI Analysis

This work addresses a bottleneck in NAS for researchers and practitioners by enabling exploration of more complex architectures, though it is incremental as it builds upon existing weight-sharing approaches.

The paper tackles the problem of neural architecture search (NAS) in complicated search spaces with long-distance connections, where existing weight-sharing algorithms fail due to interleaved connections, and presents IF-NAS, a periodic sampling algorithm that avoids these connections and outperforms random sampling and previous methods by a significant margin.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes