Related papers: A Consistent Lebesgue Measure for Multi-label Lear…
In this paper we refine the process of computing calibration functions for a number of multiclass classification surrogate losses. Calibration functions are a powerful tool for easily converting bounds for the surrogate risk (which can be…
Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs)…
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…
Large language models (LLMs) perform in-context learning (ICL) with minimal supervised examples, which benefits various natural language processing (NLP) tasks. One of the critical research focus is the selection of prompt demonstrations.…
Machine learning-based classifiers are commonly evaluated by metrics like accuracy, but deeper analysis is required to understand their strengths and weaknesses. MLMC is a visual exploration tool that tackles the challenge of multi-label…
Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to…
Empirical risk minimization (ERM) with a computationally feasible surrogate loss is a widely accepted approach for classification. Notably, the convexity and calibration (CC) properties of a loss function ensure consistency of ERM in…
We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case…
Large language models (LLMs) have achieved remarkable performance but face critical challenges: hallucinations and high inference costs. Leveraging multiple experts offers a solution: deferring uncertain inputs to more capable experts…
In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels…
In-context learning (ICL) is the ability of a large language model (LLM) to learn a new task from a few demonstrations presented as part of the context. Past studies have attributed a large portion of the success of ICL to the way these…
In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models. Deep neural network methods usually jointly embed the feature and label information…
In multi-objective learning (MOL), several possibly competing prediction tasks must be solved jointly by a single model. Achieving good trade-offs may require a model class $\mathcal{G}$ with larger capacity than what is necessary for…
Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance. In pool-based active learning, accessible unlabeled data…
Continual Learning aims to learn from a stream of tasks, being able to remember at the same time both new and old tasks. While many approaches were proposed for single-class classification, multi-label classification in the continual…
Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features…
Semi-supervised learning (SSL) has been proven beneficial for mitigating the issue of limited labeled data especially on the task of volumetric medical image segmentation. Unlike previous SSL methods which focus on exploring highly…
DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of…
Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation…
Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…