Non-negative Positive-Unlabeled (nnPU) and unbiased Positive-Unlabeled (uPU) learning reproductive code on MNIST and CIFAR10

[ICML2020] "Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training" by Xuxi Chen, Wuyang Chen, Tianlong Chen, Ye Yuan, Chen Gong, Kewei Chen, Zhangyang Wang

Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlight)

[MICCAI 2022] ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation

A collection of notebooks that implement algorithms introduced in "Learning from positive and unlabeled data: a survey"

uPU, nnPU and PN learning with Extra Trees classifier.

Official Tensorflow implementation for Deep Generative Positive-Unlabeled Learning under Selection Bias (VAE-PU) in CIKM 2020.

A PU-learning tool on spark

Source code & appendices accompanying the AAAI2022 paper "Unifying Knowledge Base Completion with PU Learning to Mitigate the Observation Bias"

Software implementation of the manuscript "A Two-step Anomaly detection Based Method for PU Classification in Imbalanced Data Sets".

A template for a PU Bagging approach. PU bagging is effective when reliable negatives can't be identified in unlabeled data. Bootstrapping creates resampled subsets, helping the model distinguish true positives from true negatives. This process infers the negative class distribution, improving classification and model robustness.

Implementation of the paper: Towards Improved Illicit Node Detection with Positive-Unlabelled Learning

PU Hellinger Trees is a technique for positive and unlabeled imbalanced data.

Software implementation of a manuscript submitted to Information Sciences

Project - Semi-supervised learning Anomaly detection in Multivariate Timeseries