μDARTS: Model Uncertainty-Aware Differentiable Architecture Search

Abstract

We present a Model Uncertainty-aware Differentiable ARchiTecture Search (μDARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty. We introduce concrete dropout within DARTS cells and include a Monte-Carlo regularizer within the training loss to optimize the concrete dropout probabilities. A predictive variance term is introduced in the validation loss to enable searching for architecture with minimal model uncertainty. The experiments on CIFAR10, CIFAR100, SVHN, and ImageNet verify the effectiveness of μDARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from μDARTS shows higher robustness to noise at the input image and model parameters compared to the architecture obtained from existing DARTS methods.