Related papers: CrossAug: A Contrastive Data Augmentation Method f…

Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designed and model-based…

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

Abstractive summarization systems based on pretrained language models often generate coherent but factually inconsistent sentences. In this paper, we present a counterfactual data augmentation approach where we augment data with perturbed…

Text augmentation is an effective technique for addressing the problem of insufficient data in natural language processing. However, existing text augmentation methods tend to focus on few-shot scenarios and usually perform poorly on large…

Diffusion models have achieved remarkable success in generative modeling. However, this study confirms the existence of overfitting in diffusion model training, particularly in data-limited regimes. To address this challenge, we propose…

In real-world machine learning systems, labels are often derived from user behaviors that the system wishes to encourage. Over time, new models must be trained as new training examples and features become available. However, feedback loops…

We study generating abstractive summaries that are faithful and factually consistent with the given articles. A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive training data, and…

Graph augmentation with contrastive learning has gained significant attention in the field of recommendation systems due to its ability to learn expressive user representations, even when labeled data is limited. However, directly applying…

Reporting bias arises when people assume that some knowledge is universally understood and hence, do not necessitate explicit elaboration. In this paper, we focus on the wide existence of reporting bias in visual-language datasets, embodied…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Counterfactual data augmentation (CDA) is a method for controlling information or biases in training datasets by generating a complementary dataset with typically opposing biases. Prior work often either relies on hand-crafted rules or…

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with…

Data augmentation is a dominant method for reducing model overfitting and improving generalization. Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i.e.}, increasing the amplitude of…

In sequential recommendation systems, data augmentation and contrastive learning techniques have recently been introduced using diffusion models to achieve robust representation learning. However, most of the existing approaches use random…

Fact verification requires validating a claim in the context of evidence. We show, however, that in the popular FEVER dataset this might not necessarily be the case. Claim-only classifiers perform competitively with top evidence-aware…

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using…

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts…

Despite substantial progress in abstractive text summarization to generate fluent and informative texts, the factual inconsistency in the generated summaries remains an important yet challenging problem to be solved. In this paper, we…

Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to…