Related papers: Improving Classifier Robustness through Active Gen…

Counterfactual analysis is central to education market design and provides a foundation for credible policy recommendations. We develop a novel methodology for counterfactual analysis in Gale-Shapley deferred-acceptance (DA) assignment…

Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training…

Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of…

Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs for…

Many pairwise classification tasks, such as paraphrase detection and open-domain question answering, naturally have extreme label imbalance (e.g., $99.99\%$ of examples are negatives). In contrast, many recent datasets heuristically choose…

Explainable machine learning has attracted much interest in the community where the stakes are high. Counterfactual explanations methods have become an important tool in explaining a black-box model. The recent advances have leveraged the…

We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a variational…

Relation extraction (RE) tasks show promising performance in extracting relations from two entities mentioned in sentences, given sufficient annotations available during training. Such annotations would be labor-intensive to obtain in…

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

In the past decade, we have experienced a massive boom in the usage of digital solutions in higher education. Due to this boom, large amounts of data have enabled advanced data analysis methods to support learners and examine learning…

The field of generating recommendations within the framework of causal inference has seen a recent surge, with recommendations being likened to treatments. This approach enhances insights into the influence of recommendations on user…

Self-supervised contrastive learning has emerged as a powerful tool in machine learning and computer vision to learn meaningful representations from unlabeled data. Meanwhile, its empirical success has encouraged many theoretical studies to…

NLP models are used in a variety of critical social computing tasks, such as detecting sexist, racist, or otherwise hateful content. Therefore, it is imperative that these models are robust to spurious features. Past work has attempted to…

Explainable artificial intelligence (XAI) has become increasingly important in decision-critical domains such as healthcare, finance, and law. Counterfactual (CF) explanations, a key approach in XAI, provide users with actionable insights…

State-of-the-art models for keyphrase generation require large amounts of training data to achieve good performance. However, obtaining keyphrase-labeled documents can be challenging and costly. To address this issue, we present a…

Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating…

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffusion models for data…

The counterfactual token generation has been limited to perturbing only a single token in texts that are generally short and single sentences. These tokens are often associated with one of many sensitive attributes. With limited…

Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLP-related augmentation methods cannot directly produce the available…