Related papers: Data Debiasing with Datamodels (D3M): Improving Su…

We tackle the problem of bias mitigation of algorithmic decisions in a setting where both the output of the algorithm and the sensitive variable are continuous. Most of prior work deals with discrete sensitive variables, meaning that the…

The subpopulationtion shift, characterized by a disparity in subpopulation distributibetween theween the training and target datasets, can significantly degrade the performance of machine learning models. Current solutions to subpopulation…

Class imbalance and distributional differences in large datasets present significant challenges for classification tasks machine learning, often leading to biased models and poor predictive performance for minority classes. This work…

When training a machine learning classifier on data where one of the classes is intrinsically rare, the classifier will often assign too few sources to the rare class. To address this, it is common to up-weight the examples of the rare…

Model selection requires repeatedly evaluating models on a given dataset and measuring their relative performances. In modern applications of machine learning, the models being considered are increasingly more expensive to evaluate and the…

Language Representation Models (LRMs) trained with real-world data may capture and exacerbate undesired bias and cause unfair treatment of people in various demographic groups. Several techniques have been investigated for applying…

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification,…

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.…

Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of…

In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective. When focussing on the way in which the training data are…

Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle. They are prone to overfitting on their training distribution and are easily fooled by small adversarial perturbations. In this…

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

We study the problem of few-shot learning-based denoising where the training set contains just a handful of clean and noisy samples. A solution to mitigate the small training set issue is to pre-train a denoising model with small training…

Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR. However, how pre-training data affects S3Ms' downstream behavior remains an unexplored issue. In this paper, we study how…

Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correlations, between input samples and the target labels, wrongly…

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other…

Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target. In this paper, we focus on the…

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…