Learnable Embedding Space for Efficient Neural Architecture Compression

Shengcao Cao, Xiaofang Wang, Kris M. Kitani

Abstract: We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search. Given a teacher network, we search for a compressed network architecture by using Bayesian Optimization (BO) with a kernel function defined over our proposed embedding space to select architectures for evaluation. We demonstrate that our search algorithm can significantly outperform various baseline methods, such as random search and reinforcement learning (Ashok et al., 2018). The compressed architectures found by our method are also better than the state-of-the-art manually-designed compact architecture ShuffleNet (Zhang et al., 2018). We also demonstrate that the learned embedding space can be transferred to new settings for architecture search, such as a larger teacher network or a teacher network in a different architecture family, without any training.

Keywords: Network Compression, Neural Architecture Search, Bayesian Optimization, Architecture Embedding

TL;DR: We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search.

Code: [ Friedrich1006/ESNAC](https://github.com/Friedrich1006/ESNAC) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=S1xLN3C9YX)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1902.00383/code)