相关论文: Robust Logistic Regression using Shift Parameters …

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the…

Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many machine learning techniques. In this paper we propose a…

Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical…

Natural language inference (NLI) aims at predicting the relationship between a given pair of premise and hypothesis. However, several works have found that there widely exists a bias pattern called annotation artifacts in NLI datasets,…

Text-based automated Cognitive Distortion detection is a challenging task due to its subjective nature, with low agreement scores observed even among expert human annotators, leading to unreliable annotations. We explore the use of Large…

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…

Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. In this paper,…

Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and generalizability of models trained through supervised learning…

As machine learning (ML) models are increasingly used in social domains to make consequential decisions about humans, they often have the power to reshape data distributions. Humans, as strategic agents, continuously adapt their behaviors…

There are inevitably many mislabeled data in real-world datasets. Because deep neural networks (DNNs) have an enormous capacity to memorize noisy labels, a robust training scheme is required to prevent labeling errors from degrading the…

Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…

Real-world datasets commonly exhibit noisy labels and class imbalance, such as long-tailed distributions. While previous research addresses this issue by differentiating noisy and clean samples, reliance on information from predictions…

For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

Q-learning is a regression-based approach that is widely used to formalize the development of an optimal dynamic treatment strategy. Finite dimensional working models are typically used to estimate certain nuisance parameters, and…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious…

Many popular linear classifiers, such as logistic regression, boosting, or SVM, are trained by optimizing a margin-based risk function. Traditionally, these risk functions are computed based on a labeled dataset. We develop a novel…

Large Language Models, despite their power, have a fundamental architectural vulnerability stemming from their causal transformer design -- order sensitivity. This architectural constraint may distorts classification outcomes when prompt…

Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that…