Related papers: Deep F-measure Maximization for End-to-End Speech …

Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are…

This paper presents the performance of a classifier built using the stackingC algorithm in nine different data sets. Each data set is generated using a sampling technique applied on the original imbalanced data set. Five new sampling…

Federated Learning (FL) is a distributed machine learning framework that trains accurate global models while preserving clients' privacy-sensitive data. However, most FL approaches assume that clients possess labeled data, which is often…

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…

Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on…

Class imbalance severely impacts machine learning performance on minority classes in real-world applications. While various solutions exist, active learning offers a fundamental fix by strategically collecting balanced, informative labeled…

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…

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…

Semi-supervised learning (SSL) has long been proved to be an effective technique to construct powerful models with limited labels. In the existing literature, consistency regularization-based methods, which force the perturbed samples to…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Class imbalance problem is commonly faced while developing machine learning models for real-life issues. Due to this problem, the fitted model tends to be biased towards the majority class data, which leads to lower precision, recall, AUC,…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

Large Language models (LLMs) are trained on large amounts of data, which can include sensitive information that may compromise personal privacy. LLMs showed to memorize parts of the training data and emit those data verbatim when an…

Data pruning, which aims to downsize a large training set into a small informative subset, is crucial for reducing the enormous computational costs of modern deep learning. Though large-scale data collections invariably contain annotation…

Interpreting the inference-time behavior of deep neural networks remains a challenging problem. Existing approaches to counterfactual explanation typically ask: What is the closest alternative input that would alter the model's prediction…

Active Learning (AL) techniques have proven to be highly effective in reducing data labeling costs across a range of machine learning tasks. Nevertheless, one known challenge of these methods is their potential to introduce unfairness…

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers…

Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.…