Related papers: Mitigating Label Bias via Decoupled Confident Lear…

With the ever-increasing cases of hate spread on social media platforms, it is critical to design abuse detection mechanisms to proactively avoid and control such incidents. While there exist methods for hate speech detection, they…

Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting, where trivial…

How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim…

Deep Learning with noisy labels is a practically challenging problem in weakly supervised learning. The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the…

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Vision-language models are growing in popularity and public visibility to generate, edit, and caption images at scale; but their outputs can perpetuate and amplify societal biases learned during pre-training on uncurated image-text pairs…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…

Machine learning systems are increasingly being used to make impactful decisions such as loan applications and criminal justice risk assessments, and as such, ensuring fairness of these systems is critical. This is often challenging as the…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining how models with minimal safety alignment (uncensored) compare with more heavily aligned (censored) counterparts in a…

Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bias mitigation methods typically involve either a)…

Federated learning has gained great attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple parties. As a sub-category, vertical federated learning (vFL) focuses on the scenario where features…

Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our investigation reveals that the embedding space of existing…

Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a method to identity suspected noisy labels and then correct…

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…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…

Federated Learning (FL) is a powerful framework for privacy-preserving distributed learning. It enables multiple clients to collaboratively train a global model without sharing raw data. However, handling noisy labels in FL remains a major…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

We consider an online learning problem with one-sided feedback, in which the learner is able to observe the true label only for positively predicted instances. On each round, $k$ instances arrive and receive classification outcomes…

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes…