# Robust Deep Ordinal Regression Under Label Noise

arXiv: https://arxiv.org/abs/1912.03488 · HTML: https://mlsanity.com/paper/1912.03488/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Learning with Density Matrices and Random Features](https://mlsanity.com/paper/2102.04394/) (2021)
- [Learning semantic image quality for fetal ultrasound from noisy ranking annotation](https://mlsanity.com/paper/2402.08294/) (2024)
- [Sample Selection via Contrastive Fragmentation for Noisy Label Regression](https://mlsanity.com/paper/2502.17771/) (2025)
- [Learning Disease State from Noisy Ordinal Disease Progression Labels](https://mlsanity.com/paper/2503.10440/) (2025)
- [Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels](https://mlsanity.com/paper/2410.21885/) (2024)
- [DFORD: Directional Feedback based Online Ordinal Regression Learning](https://mlsanity.com/paper/2512.19550/) (2025)
- [Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data](https://mlsanity.com/paper/2607.08103/) (2026)

## Abstract (arXiv)

The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account. We propose a theoretically grounded approach for class conditional label noise in ordinal regression problems. We present a deep learning implementation of two commonly used loss functions for ordinal regression that is both - 1) robust to label noise, and 2) rank consistent for a good ranking rule. We verify these properties of the algorithm empirically and show robustness to label noise on real data and rank consistency. To the best of our knowledge, this is the first approach for robust ordinal regression models.