Positive unlabeled learning with tensor networks

TL;DR

This paper introduces a domain-agnostic tensor network method for positive unlabeled learning that improves accuracy and can generate new samples, applicable to various data types including images and categorical data.

Contribution

It presents a novel tensor network approach that enhances positive unlabeled learning and enables generative modeling across diverse data domains.

Findings

Significant improvement over state-of-the-art on MNIST and other datasets.

Method is not domain-specific, applicable to images and categorical data.

Tensor network model can generate new positive and negative samples.

Abstract

Positive unlabeled learning is a binary classification problem with positive and unlabeled data. It is common in domains where negative labels are costly or impossible to obtain, e.g., medicine and personalized advertising. Most approaches to positive unlabeled learning apply to specific data types (e.g., images, categorical data) and can not generate new positive and negative samples. This work introduces a feature-space distance-based tensor network approach to the positive unlabeled learning problem. The presented method is not domain specific and significantly improves the state-of-the-art results on the MNIST image and 15 categorical/mixed datasets. The trained tensor network model is also a generative model and enables the generation of new positive and negative instances.