BayesNAS: A Bayesian Approach for Neural Architecture Search

Abstract

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an over-parameterized network. However, there are two issues associated with most one-shot NAS methods. First, dependencies between a node and its predecessors and successors are often disregarded which result in improper treatment over zero operations. Second, architecture parameters pruning based on their magnitude is questionable. In this paper, we employ the classic Bayesian learning approach to alleviate these two issues by modeling architecture parameters using hierarchical automatic relevance determination (HARD) priors. Unlike other NAS methods, we train the over-parameterized network for only one epoch then update the architecture. Impressively, this enabled us to find the architecture on CIFAR-10 within only 0.2 GPU days using a single GPU. Competitive performance can be also achieved by transferring to ImageNet. As a byproduct, our approach can be applied directly to compress convolutional neural networks by enforcing structural sparsity which achieves extremely sparse networks without accuracy deterioration.

International Conference on Machine Learning 2019

Cited by in corpus (16)

• Rethinking Architecture Selection in Differentiable NAS
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Search to aggregate neighborhood for graph neural network
• High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
• NASGEM: Neural Architecture Search via Graph Embedding Method
• Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• A Sparse Bayesian Deep Learning Approach for Identification of Cascaded Tanks Benchmark
• Interleaving Learning, with Application to Neural Architecture Search
• Learning by Self-Explanation, with Application to Neural Architecture Search
• iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization
• An Analysis of Super-Net Heuristics in Weight-Sharing NAS
• Discretization-Aware Architecture Search
• Small-Group Learning, with Application to Neural Architecture Search
• Neural Architecture Search via Bregman Iterations
• NAS-FCOS: Efficient Search for Object Detection Architectures