Robustness to Spurious Correlations via Human Annotations

• URL: http://arxiv.org/abs/2007.06661v2
• Date: Thu, 13 Aug 2020 22:48:37 GMT
• Title: Robustness to Spurious Correlations via Human Annotations
• Authors: Megha Srivastava, Tatsunori Hashimoto, Percy Liang
• Abstract summary: We present a framework for making models robust to spurious correlations by leveraging humans' common sense knowledge of causality. Specifically, we use human annotation to augment each training example with a potential unmeasured variable. We then introduce a new distributionally robust optimization objective over unmeasured variables (UV-DRO) to control the worst-case loss over possible test-time shifts.
• Score: 100.63051542531171
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, unmeasured variables, such as confounders, break this assumption---useful correlations between features and labels at training time can become useless or even harmful at test time. For example, high obesity is generally predictive for heart disease, but this relation may not hold for smokers who generally have lower rates of obesity and higher rates of heart disease. We present a framework for making models robust to spurious correlations by leveraging humans' common sense knowledge of causality. Specifically, we use human annotation to augment each training example with a potential unmeasured variable (i.e. an underweight patient with heart disease may be a smoker), reducing the problem to a covariate shift problem. We then introduce a new distributionally robust optimization objective over unmeasured variables (UV-DRO) to control the worst-case loss over possible test-time shifts. Empirically, we show improvements of 5-10% on a digit recognition task confounded by rotation, and 1.5-5% on the task of analyzing NYPD Police Stops confounded by location.

Related papers

• Catastrophic Overfitting: A Potential Blessing in Disguise [51.996943482875366]
  Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Although existing FAT approaches have made strides in mitigating CO, the ascent of adversarial robustness occurs with a non-negligible decline in classification accuracy on clean samples. We employ the feature activation differences between clean and adversarial examples to analyze the underlying causes of CO. We harness CO to achieve attack obfuscation', aiming to bolster model performance.
  arXiv  Detail & Related papers  (2024-02-28T10:01:44Z)
• Robust Learning via Conditional Prevalence Adjustment [7.480241867887245]
  Deep learning models might fail catastrophically in unseen sites. We propose a method called CoPA (Conditional Prevalence-Adjustment) for anti-causal tasks.
  arXiv  Detail & Related papers  (2023-10-24T12:13:49Z)
• Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation [57.351098530477124]
  We consider one critical type of robustness against spurious correlation, where different portions of the state do not have correlations induced by unobserved confounders. A model that learns such useless or even harmful correlation could catastrophically fail when the confounder in the test case deviates from the training one. Existing robust algorithms that assume simple and unstructured uncertainty sets are therefore inadequate to address this challenge.
  arXiv  Detail & Related papers  (2023-07-15T23:53:37Z)
• Automatic diagnosis of knee osteoarthritis severity using Swin transformer [55.01037422579516]
  Knee osteoarthritis (KOA) is a widespread condition that can cause chronic pain and stiffness in the knee joint. We propose an automated approach that employs the Swin Transformer to predict the severity of KOA.
  arXiv  Detail & Related papers  (2023-07-10T09:49:30Z)
• Semantic Latent Space Regression of Diffusion Autoencoders for Vertebral Fracture Grading [72.45699658852304]
  This paper proposes a novel approach to train a generative Diffusion Autoencoder model as an unsupervised feature extractor. We model fracture grading as a continuous regression, which is more reflective of the smooth progression of fractures. Importantly, the generative nature of our method allows us to visualize different grades of a given vertebra, providing interpretability and insight into the features that contribute to automated grading.
  arXiv  Detail & Related papers  (2023-03-21T17:16:01Z)
• Algorithmic encoding of protected characteristics and its implications on disparities across subgroups [17.415882865534638]
  Machine learning models may pick up undesirable correlations between a patient's racial identity and clinical outcome. Very little is known about how these biases are encoded and how one may reduce or even remove disparate performance.
  arXiv  Detail & Related papers  (2021-10-27T20:30:57Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts [11.511323714777298]
  This paper studies the case of spurious class skew in which patients with a particular attribute are spuriously more likely to have the outcome of interest. We show that deep nets can accurately identify many patient attributes including sex (AUROC = 0.96) and age (AUROC >= 0.90) when learning to predict a diagnosis. A simple transfer learning approach is surprisingly effective at preventing the shortcut and promoting good performance.
  arXiv  Detail & Related papers  (2020-09-21T18:52:43Z)
• Improving Calibration through the Relationship with Adversarial Robustness [19.384119330332446]
  We study the connection between adversarial robustness and calibration. We propose Adversarial Robustness based Adaptive Labeling (AR-AdaLS) We find that our method, taking the adversarial robustness of the in-distribution data into consideration, leads to better calibration over the model even under distributional shifts.
  arXiv  Detail & Related papers  (2020-06-29T20:56:33Z)

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.