相关论文: Explaining The Efficacy of Counterfactually Augmen…

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a…

Speech emotion recognition is an important component of any human centered system. But speech characteristics produced and perceived by a person can be influenced by a multitude of reasons, both desirable such as emotion, and undesirable…

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the…

Data augmentation is one of the most successful techniques to improve the classification accuracy of machine learning models in computer vision. However, applying data augmentation to tabular data is a challenging problem since it is hard…

Despite the evolution of language models, they continue to portray harmful societal biases and stereotypes inadvertently learned from training data. These inherent biases often result in detrimental effects in various applications.…

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be…

In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution…

Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that…

Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character; e.g., changing the gender of a…

Active Learning (AL) allows models to learn interactively from user feedback. This paper introduces a counterfactual data augmentation approach to AL, particularly addressing the selection of datapoints for user querying, a pivotal concern…

Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability. Moreover additional restrictions are often imposed in order to simplify the inference task: this is the case for…

Causal modeling has been recognized as a potential solution to many challenging problems in machine learning (ML). Here, we describe how a recently proposed counterfactual approach developed to deconfound linear structural causal models can…

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…

Unsupervised Data Augmentation (UDA) is a semi-supervised technique that applies a consistency loss to penalize differences between a model's predictions on (a) observed (unlabeled) examples; and (b) corresponding 'noised' examples produced…

Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not independent, their interactions are often sparse, and the…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for…

Models that learn spurious correlations from training data often fail when deployed in new environments. While many methods aim to learn invariant representations to address this, they often underperform standard empirical risk minimization…

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability. The general approach to this task is to train a large pretrained language model on a specific dataset.…