Cyclic Differentiable Architecture Search

Abstract

Differentiable ARchiTecture Search, i.e., DARTS, has drawn great attention in neural architecture search. It tries to find the optimal architecture in a shallow search network and then measures its performance in a deep evaluation network. The independent optimization of the search and evaluation networks, however, leaves room for potential improvement by allowing interaction between the two networks. To address the problematic optimization issue, we propose new joint optimization objectives and a novel Cyclic Differentiable ARchiTecture Search framework, dubbed CDARTS. Considering the structure difference, CDARTS builds a cyclic feedback mechanism between the search and evaluation networks with introspective distillation. First, the search network generates an initial architecture for evaluation, and the weights of the evaluation network are optimized. Second, the architecture weights in the search network are further optimized by the label supervision in classification, as well as the regularization from the evaluation network through feature distillation. Repeating the above cycle results in joint optimization of the search and evaluation networks and thus enables the evolution of the architecture to fit the final evaluation network. The experiments and analysis on CIFAR, ImageNet and NAS-Bench-201 demonstrate the effectiveness of the proposed approach over the state-of-the-art ones. Specifically, in the DARTS search space, we achieve 97.52% top-1 accuracy on CIFAR10 and 76.3% top-1 accuracy on ImageNet. In the chain-structured search space, we achieve 78.2% top-1 accuracy on ImageNet, which is 1.1% higher than EfficientNet-B0. Our code and models are publicly available at https://github.com/microsoft/Cream.

arXiv commentAccepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

References in corpus (26)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• mixup: Beyond Empirical Risk Minimization
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Wide Residual Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• DARTS: Differentiable Architecture Search
• Neural Architecture Optimization
• PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• DARTS+: Improved Differentiable Architecture Search with Early Stopping
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• One-Shot Neural Architecture Search via Self-Evaluated Template Network
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• NAS evaluation is frustratingly hard
• ASAP: Architecture Search, Anneal and Prune
• Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
• Towards Oracle Knowledge Distillation with Neural Architecture Search
• MoGA: Searching Beyond MobileNetV3
• Search to Distill: Pearls are Everywhere but not the Eyes

Cited by in corpus (6)

• EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Neural Architecture Search by Estimation of Network Structure Distributions
• Single-level Optimization For Differential Architecture Search
• Single-DARTS: Towards Stable Architecture Search
• Mutually-aware Sub-Graphs Differentiable Architecture Search