# Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning

arXiv: https://arxiv.org/abs/2510.01278 · HTML: https://mlsanity.com/paper/2510.01278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Selective-Supervised Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2203.04181/) (2022)
- [Towards the Generalization of Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2111.00743/) (2021)
- [Mixture Proportion Estimation via Kernel Embedding of Distributions](https://mlsanity.com/paper/1603.02501/) (2016)
- [Mixture Proportion Estimation and PU Learning: A Modern Approach](https://mlsanity.com/paper/2111.00980/) (2021)
- [PU Learning for Matrix Completion](https://mlsanity.com/paper/1411.6081/) (2014)
- [Twin Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2303.06930/) (2023)
- [PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning](https://mlsanity.com/paper/2201.08984/) (2022)
- [f-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning](https://mlsanity.com/paper/2402.10150/) (2024)
- [Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends](https://mlsanity.com/paper/2310.04078/) (2023)
- [Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization](https://mlsanity.com/paper/2210.08461/) (2022)
- [Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery](https://mlsanity.com/paper/2308.15081/) (2023)
- [One-Class Risk Estimation for One-Class Hyperspectral Image Classification](https://mlsanity.com/paper/2210.15457/) (2022)
- [Representation Learning via Non-Contrastive Mutual Information](https://mlsanity.com/paper/2504.16667/) (2025)
- [Semantic Concentration for Self-Supervised Dense Representations Learning](https://mlsanity.com/paper/2509.09429/) (2025)
- [Building Damage Mapping with Self-PositiveUnlabeled Learning](https://mlsanity.com/paper/2111.02586/) (2021)
- [Weakly-Supervised Contrastive Learning for Imprecise Class Labels](https://mlsanity.com/paper/2505.22028/) (2025)

## Built on by (most cited first, 1 of 1)

- [Positive-Unlabeled Learning for Agent Safety False Alarm Auditing](https://mlsanity.com/paper/2610.02925/) (2026)

## Abstract (arXiv)

Positive-Unlabeled (PU) learning aims to train a binary classifier (positive vs. negative) where only limited positive data and abundant unlabeled data are available. While widely applicable, state-of-the-art PU learning methods substantially underperform their supervised counterparts on complex datasets, especially without auxiliary negatives or pre-estimated parameters (e.g., a 14.26% gap on CIFAR-100 dataset). We identify the primary bottleneck as the challenge of learning discriminative representations under unreliable supervision. To tackle this challenge, we propose NcPU, a non-contrastive PU learning framework that requires no auxiliary information. NcPU combines a noisy-pair robust supervised non-contrastive loss (NoiSNCL), which aligns intra-class representations despite unreliable supervision, with a phantom label disambiguation (PLD) scheme that supplies conservative negative supervision via regret-based label updates. Theoretically, NoiSNCL and PLD can iteratively benefit each other from the perspective of the Expectation-Maximization framework. Empirically, extensive experiments demonstrate that: (1) NoiSNCL enables simple PU methods to achieve competitive performance; and (2) NcPU achieves substantial improvements over state-of-the-art PU methods across diverse datasets, including challenging datasets on post-disaster building damage mapping, highlighting its promise for real-world applications. Code: Code will be open-sourced after review.