paper-with-me

홈 › Papers

Multi-Label Bayesian Active Learning with Inter-Label Relationships

2024-11-26 · Yuanyuan Qi, Jueqing Lu, Xiaohao Yang, Joanne Enticott, Lan Du

The primary challenge of multi-label active learning, differing it from multi-class active learning, lies in assessing the informativeness of an indefinite number of labels while also accounting for the inherited label correlation. Existing studies either require substantial computational resources to leverage correlations or fail to fully explore label dependencies. Additionally, real-world scenarios often require addressing intrinsic biases stemming from imbalanced data distributions. In this paper, we propose a new multi-label active learning strategy to address both challenges. Our method incorporates progressively updated positive and negative correlation matrices to capture co-occurrence and disjoint relationships within the label space of annotated samples, enabling a holistic assessment of uncertainty rather than treating labels as isolated elements. Furthermore, alongside diversity, our model employs ensemble pseudo labeling and beta scoring rules to address data imbalances. Extensive experiments on four realistic datasets demonstrate that our strategy consistently achieves more reliable and superior performance, compared to several established methods.

📄 PDF Abstract BibTeX arXiv:2411.17941

Code (1)

qijindou/CRAB pytorch

Tasks

Active LearningDiversityInformativeness

Similar Papers 제목 키워드 기반

Interactive Event Sifting using Bayesian Graph Neural Networks

2024-10-07 · José Nascimento, Nathan Jacobs, Anderson Rocha

Forensic analysts often use social media imagery and texts to understand important events. A primary challenge is the initial sifting of irrelevant posts. This work introduces an interactive process for training an event…

Active Learning

Deep Bayesian Active Learning, A Brief Survey on Recent Advances

2020-12-15 · Salman Mohamadi, Hamidreza Amindavar

Active learning frameworks offer efficient data annotation without remarkable accuracy degradation. In other words, active learning starts training the model with a small size of labeled data while exploring the space of…

Active LearningSurvey

Active Bayesian Assessment for Black-Box Classifiers

2020-02-16 · Disi Ji, Robert L. Logan IV, Padhraic Smyth, Mark Steyvers

Recent advances in machine learning have led to increased deployment of black-box classifiers across a wide variety of applications. In many such situations there is a critical need to both reliably assess the performanc…

text-classificationText Classification

Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning

2019-05-17 · Mike Walmsley, Lewis Smith, Chris Lintott, Yarin Gal 외

We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncer…

Active Learning

Making Better Use of Unlabelled Data in Bayesian Active Learning

2024-04-26 · Freddie Bickford Smith, Adam Foster, Tom Rainforth

Fully supervised models are predominant in Bayesian active learning. We argue that their neglect of the information present in unlabelled data harms not just predictive performance but also decisions about what data to a…

Active Learning