• Home
  • Search
  • Multi-Class Positive and Unlabeled Learning for High Dimensional Data Based on Outlier Detection in a Low Dimensional Embedding Space
  • Cite Icon2
  • https://doi.org/10.3390/electronics11172789Copy DOI Icon

Multi-Class Positive and Unlabeled Learning for High Dimensional Data Based on Outlier Detection in a Low Dimensional Embedding Space

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Positive and unlabeled (PU) learning targets a binary classifier on labeled positive data and unlabeled data containing data samples of positive and unknown negative classes, whereas multi-class positive and unlabeled (MPU) learning aims to learn a multi-class classifier assuming labeled data from multiple positive classes. In this paper, we propose a two-step approach for MPU learning on high dimensional data. In the first step, negative samples are selected from unlabeled data using an ensemble of k-nearest neighbors-based outlier detection models in a low dimensional space which is embedded by a linear discriminant function. We present an approach for binary prediction which determines whether a data sample is a negative data sample. In the second step, the linear discriminant function is optimized on the labeled positive data and negative samples selected in the first step. It alternates between updating the parameters of the linear discriminant function and selecting reliable negative samples by detecting outliers in a low-dimensional space. Experimental results using high dimensional text data demonstrate the high performance of the proposed MPU learning method.

Loading PDF

Similar Papers
  • PDF
  • Research Article
  • Citations1

Positive and unlabeled learning from hospital administrative data: a novel approach to identify sepsis cases.

  • Oct 28, 2025
  • Health care management science
  • Justus Vogel +1
  • Research Article

Discriminative-Generative Positive and Unlabeled Learning.

  • Jan 01, 2026
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Botai Yuan +3
  • Conference Article
  • Citations21

Positive and Unlabeled Learning for Anomaly Detection with Multi-features

  • Oct 19, 2017
  • Jiaqi Zhang +3
  • Conference Article
  • Citations2

Differential Privacy for Positive and Unlabeled Learning With Known Class Priors

  • Jun 01, 2018
  • Anh T Pham +1
  • Conference Article
  • Citations44

Positive and Unlabeled Learning with Label Disambiguation

  • Aug 01, 2019
  • Chuang Zhang +4
  • Research Article
  • Citations7

Weighted Contrastive Learning With Hard Negative Mining for Positive and Unlabeled Learning.

  • Jun 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Botai Yuan +3
  • Research Article
  • Citations45

Boosting Positive and Unlabeled Learning for Anomaly Detection With Multi-Features

  • May 01, 2019
  • IEEE Transactions on Multimedia
  • Jiaqi Zhang +4
  • Research Article
  • Citations23

Improving Neural Relation Extraction with Positive and Unlabeled Learning

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zhengqiu He +5
  • Research Article
  • Citations7

A loss matrix-based alternating optimization method for sparse PU learning

  • Dec 01, 2022
  • Swarm and Evolutionary Computation
  • Jianfeng Qiu +3
  • Conference Article
  • Citations56

Multi-Positive and Unlabeled Learning

  • Aug 01, 2017
  • Yixing Xu +3
  • Research Article
  • Citations4

A recent survey on instance-dependent positive and unlabeled learning

  • Oct 12, 2022
  • Fundamental research
  • Chen Gong +4
  • Research Article

Detecting Uncoded Self-Harm in Veterans\u2019 Electronic Health Records Using Positive and Unlabeled Learning: Retrospective Cohort Study

  • Jun 04, 2026
  • Journal of Medical Internet Research
  • Praveen Kumar +16
  • Conference Article
  • Citations5

Positive Unlabeled Learning by Semi-Supervised Learning

  • Oct 16, 2022
  • Zhuowei Wang +2
  • Book Chapter
  • Citations11

Towards Positive Unlabeled Learning for Parallel Data Mining: A Random Forest Framework

  • Jan 01, 2014
  • Chen Li +1
  • Research Article
  • Citations2

A multi-objective evolutionary algorithm for robust positive-unlabeled learning

  • Jun 12, 2024
  • Information Sciences
  • Jianfeng Qiu +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.