Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift

Abstract

A novel variational inference based resampling framework is proposed to evaluate the robustness and generalization capability of deep learning models with respect to distribution shift. We use Auto Encoding Variational Bayes to find a latent representation of the data, on which a Variational Gaussian Mixture Model is applied to deliberately create distribution shift by dividing the dataset into different clusters. Wasserstein distance is used to characterize the extent of distribution shift between the generated data splits. We compare several popular Convolutional Neural Network (CNN) architectures and Bayesian CNN models for image classification on the Fashion-MNIST dataset, to assess their robustness and generalization behavior under the deliberately created distribution shift, as well as under random Cross Validation. Our method of creating artificial domain splits of a single dataset can also be used to establish novel model selection criteria and assessment tools in machine learning, as well as benchmark methods for domain adaptation and domain generalization approaches.

References in corpus (11)

• Auto-Encoding Variational Bayes
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Weight Uncertainty in Neural Networks
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Do ImageNet Classifiers Generalize to ImageNet?
• Variational Dropout Sparsifies Deep Neural Networks
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation
• Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization
• ReinBo: Machine Learning pipeline search and configuration with Bayesian Optimization embedded Reinforcement Learning
• Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning

Cited by in corpus (1)

• Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning