# Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative

arXiv: https://arxiv.org/abs/1901.10155 · HTML: https://mlsanity.com/paper/1901.10155/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction](https://mlsanity.com/paper/2308.00279/) (2023)
- [Community-Based Hierarchical Positive-Unlabeled (PU) Model Fusion for Chronic Disease Prediction](https://mlsanity.com/paper/2309.03386/) (2023)
- [Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2303.14898/) (2023)
- [Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning](https://mlsanity.com/paper/2211.16756/) (2022)
- [A Symmetric Loss Perspective of Reliable Machine Learning](https://mlsanity.com/paper/2101.01366/) (2021)
- [Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Data](https://mlsanity.com/paper/2203.07206/) (2022)

## Abstract (arXiv)

In the early history of positive-unlabeled (PU) learning, the sample selection approach, which heuristically selects negative (N) data from U data, was explored extensively. However, this approach was later dominated by the importance reweighting approach, which carefully treats all U data as N data. May there be a new sample selection method that can outperform the latest importance reweighting method in the deep learning age? This paper is devoted to answering this question affirmatively---we propose to label large-loss U data as P, based on the memorization properties of deep networks. Since P data selected in such a way are biased, we develop a novel learning objective that can handle such biased P data properly. Experiments confirm the superiority of the proposed method.