相关论文: Learning Effective Embeddings From Crowdsourced La…

Labeling real-world datasets is time consuming but indispensable for supervised machine learning models. A common solution is to distribute the labeling task across a large number of non-expert workers via crowd-sourcing. Due to the varying…

Crowdsourcing has attracted much attention for its convenience to collect labels from non-expert workers instead of experts. However, due to the high level of noise from the non-experts, an aggregation model that learns the true label by…

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…

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…

Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in…

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 recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

Crowdsourcing has been successfully employed in the past as an effective and cheap way to execute classification tasks and has therefore attracted the attention of the research community. However, we still lack a theoretical understanding…

Modern machine learning algorithms need large datasets to be trained. Crowdsourcing has become a popular approach to label large datasets in a shorter time as well as at a lower cost comparing to that needed for a limited number of experts.…

Partial label learning (PLL) is a significant weakly supervised learning framework, where each training example corresponds to a set of candidate labels and only one label is the ground-truth label. For the first time, this paper…

Modern neural network architectures have shown remarkable success in several large-scale classification and prediction tasks. Part of the success of these architectures is their flexibility to transform the data from the raw input…

Crowdsourcing has emerged as an alternative solution for collecting large scale labels. However, the majority of recruited workers are not domain experts, so their contributed labels could be noisy. In this paper, we propose a two-stage…

Multi-label classification (MLC) studies the problem where each instance is associated with multiple relevant labels, which leads to the exponential growth of output space. MLC encourages a popular framework named label compression (LC) for…

Crowdsourcing systems have been used to accumulate massive amounts of labeled data for applications such as computer vision and natural language processing. However, because crowdsourced labeling is inherently dynamic and uncertain,…

Learning with noisy labels has become an effective strategy for enhancing the robustness of models, which enables models to better tolerate inaccurate data. Existing methods either focus on optimizing the loss function to mitigate the…

Crowd-sourcing has become a popular means of acquiring labeled data for a wide variety of tasks where humans are more accurate than computers, e.g., labeling images, matching objects, or analyzing sentiment. However, relying solely on the…

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time…

We study crowdsourced PAC learning of threshold functions, where the labels are gathered from a pool of annotators some of whom may behave adversarially. This is yet a challenging problem and until recently has computationally and query…

An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. This paper addresses one such problem, namely how to exploit hierarchical structures over labels.…

This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign…