Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization

• URL: http://arxiv.org/abs/2002.04019v2
• Date: Tue, 25 Feb 2020 21:35:28 GMT
• Title: Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization
• Authors: Aakash Kaku, Sreyas Mohan, Avinash Parnandi, Heidi Schambra and Carlos Fernandez-Granda
• Abstract summary: Extraneous variables are variables that are irrelevant for a certain task, but heavily affect the distribution of the available data. We show that the presence of such variables can degrade the performance of deep-learning models. We show that estimating the feature statistics adaptively during inference, as in instance normalization, addresses this issue.
• Score: 17.829013101192295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extraneous variables are variables that are irrelevant for a certain task, but heavily affect the distribution of the available data. In this work, we show that the presence of such variables can degrade the performance of deep-learning models. We study three datasets where there is a strong influence of known extraneous variables: classification of upper-body movements in stroke patients, annotation of surgical activities, and recognition of corrupted images. Models trained with batch normalization learn features that are highly dependent on the extraneous variables. In batch normalization, the statistics used to normalize the features are learned from the training set and fixed at test time, which produces a mismatch in the presence of varying extraneous variables. We demonstrate that estimating the feature statistics adaptively during inference, as in instance normalization, addresses this issue, producing normalized features that are more robust to changes in the extraneous variables. This results in a significant gain in performance for different network architectures and choices of feature statistics.

Related papers

• Model-independent variable selection via the rule-based variable priority [1.2771542695459488]
  We introduce a new model-independent approach, Variable Priority (VarPro) VarPro works by utilizing rules without the need to generate artificial data or evaluate prediction error. We show that VarPro has a consistent filtering property for noise variables.
  arXiv  Detail & Related papers  (2024-09-13T17:32:05Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues [19.4921353136871]
  We study two types of distribution shifts: diversity shifts, which occur when test samples exhibit patterns unseen during training, and correlation shifts, which occur when test data present a different correlation between seen invariant and spurious features. We propose an integrated protocol to analyze both types of shifts using datasets where they co-exist in a controllable manner.
  arXiv  Detail & Related papers  (2023-05-09T23:40:23Z)
• Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift [50.98086766507025]
  We propose a simple-yet-effective data augmentation strategy, Adversarial Invariant Augmentation (AIA) AIA aims to extrapolate and generate new environments, while concurrently preserving the original stable features during the augmentation process.
  arXiv  Detail & Related papers  (2022-11-05T07:55:55Z)
• Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets [53.34152466646884]
  In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
  arXiv  Detail & Related papers  (2022-03-29T04:54:06Z)
• Uncertainty Modeling for Out-of-Distribution Generalization [56.957731893992495]
  We argue that the feature statistics can be properly manipulated to improve the generalization ability of deep learning models. Common methods often consider the feature statistics as deterministic values measured from the learned features. We improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
  arXiv  Detail & Related papers  (2022-02-08T16:09:12Z)
• Grounding inductive biases in natural images:invariance stems from variations in data [20.432568247732206]
  We study the factors of variation in a real dataset, ImageNet. We show standard augmentation relies on a precise combination of translation and scale. We find that the main factors of variation in ImageNet mostly relate to appearance.
  arXiv  Detail & Related papers  (2021-06-09T14:58:57Z)
• Metadata Normalization [54.43363251520749]
  Batch Normalization (BN) normalizes feature distributions by standardizing with batch statistics. BN does not correct the influence on features from extraneous variables or multiple distributions. We introduce the Metadata Normalization layer, a new batch-level operation which can be used end-to-end within the training framework.
  arXiv  Detail & Related papers  (2021-04-19T05:10:26Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)
• Robust Variational Autoencoder for Tabular Data with Beta Divergence [0.0]
  We propose a robust variational autoencoder with mixed categorical and continuous features. Our results on the anomaly detection application for network traffic datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-06-15T08:09:34Z)
• Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders [18.315247344611727]
  We show that VAE latent variables often focus on some factors of variation at the expense of others. We propose a regularization scheme for VAEs, which we show substantially addresses the feature imbalance problem.
  arXiv  Detail & Related papers  (2020-05-12T00:46:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.