μDARTS: Model Uncertainty-Aware Differentiable Architecture Search

We present a Model Uncertainty-aware Differentiable ARchiTecture Search ( \mu DARTS) 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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2022, Vol.10, p.98670-98682
Main Authors: Chakraborty, Biswadeep, Mukhopadhyay, Saibal
Format: Article
Language:English
Subjects:
Accuracy
Computer architecture
darts
Image classification
ImageNet
Monte Carlo dropout
Monte Carlo methods
neural architecture search
Neural networks
Optimization
Training data
Uncertainty
Uncertainty estimation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a Model Uncertainty-aware Differentiable ARchiTecture Search ( \mu DARTS) 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 \mu DARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from \mu DARTS shows higher robustness to noise at the input image and model parameters compared to the architecture obtained from existing DARTS methods.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2022.3206373