Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

• URL: http://arxiv.org/abs/2012.04104v1
• Date: Mon, 7 Dec 2020 23:08:59 GMT
• Title: Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
• Authors: Fereshte Khani, Percy Liang
• Abstract summary: A natural remedy is to remove spurious features from the model. We show that removal of spurious features can decrease accuracy due to inductive biases. We also show that robust self-training can remove spurious features without affecting the overall accuracy.
• Score: 83.68135652247496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spurious features from the model. However, in this work we show that removal of spurious features can decrease accuracy due to the inductive biases of overparameterized models. We completely characterize how the removal of spurious features affects accuracy across different groups (more generally, test distributions) in noiseless overparameterized linear regression. In addition, we show that removal of spurious feature can decrease the accuracy even in balanced datasets -- each target co-occurs equally with each spurious feature; and it can inadvertently make the model more susceptible to other spurious features. Finally, we show that robust self-training can remove spurious features without affecting the overall accuracy. Experiments on the Toxic-Comment-Detectoin and CelebA datasets show that our results hold in non-linear models.

Related papers

• Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation [70.36344590967519]
  We show that noisy data and nuisance features can be sufficient to shatter the Accuracy-on-the-line phenomenon. We demonstrate this phenomenon across both synthetic and real datasets with noisy data and nuisance features.
  arXiv  Detail & Related papers  (2024-06-27T09:57:31Z)
• 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)
• Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Data [1.76179873429447]
  We propose a data preprocessing technique that can detect instances ascribing a specific kind of bias that should be removed from the dataset before training. In particular, we claim that in the problem settings where instances exist with similar feature but different labels caused by variation in protected attributes, an inherent bias gets induced in the dataset.
  arXiv  Detail & Related papers  (2022-10-24T13:04:07Z)
• Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck [33.18197518590706]
  We propose a way of explicitly distilling feature representation into the robust and non-robust features, using Information Bottleneck. We demonstrate that the distilled features are highly correlated with adversarial prediction, and they have human-perceptible semantic information by themselves. We present an attack mechanism intensifying the gradient of non-robust features that is directly related to the model prediction, and validate its effectiveness of breaking model robustness.
  arXiv  Detail & Related papers  (2022-04-06T11:22:46Z)
• Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation [72.92329724600631]
  We propose a pseudo-attribute-based algorithm, coined Spread Spurious Attribute, for improving the worst-group accuracy. Our experiments on various benchmark datasets show that our algorithm consistently outperforms the baseline methods. We also demonstrate that the proposed SSA can achieve comparable performances to methods using full (100%) spurious attribute supervision.
  arXiv  Detail & Related papers  (2022-04-05T09:08:30Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)
• Causally Estimating the Sensitivity of Neural NLP Models to Spurious Features [19.770032728328733]
  There is no measure to evaluate or compare the effects of different forms of spurious features in NLP. We quantify model sensitivity to spurious features with a causal estimand, dubbed CENT. We find statistically significant inverse correlations between sensitivity and robustness, providing empirical support for our hypothesis.
  arXiv  Detail & Related papers  (2021-10-14T05:26:08Z)
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
  Causal mechanisms can be described by structural causal models. One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
  arXiv  Detail & Related papers  (2021-09-06T14:52:58Z)
• One Neuron to Fool Them All [12.107259467873094]
  We evaluate the sensitivity of individual neurons in terms of how robust the model's output is to direct perturbations of that neuron's output. Attacks using a loss function that targets just a single sensitive neuron find adversarial examples nearly as effectively as ones that target the full model.
  arXiv  Detail & Related papers  (2020-03-20T16:49:38Z)

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.