# Learning from Binary Labels with Instance-Dependent Corruption

arXiv: https://arxiv.org/abs/1605.00751 · HTML: https://mlsanity.com/paper/1605.00751/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2016.

## Built on by (most cited first, 5 of 5)

- [Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection](https://mlsanity.com/paper/2111.14932/) (2021)
- [Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model](https://mlsanity.com/paper/2101.05467/) (2021)
- [Meta Self-Refinement for Robust Learning with Weak Supervision](https://mlsanity.com/paper/2205.07290/) (2022)
- [Binary classification with corrupted labels](https://mlsanity.com/paper/2106.09136/) (2021)
- [The Weak Supervision Landscape](https://mlsanity.com/paper/2203.16282/) (2022)

## Abstract (arXiv)

Suppose we have a sample of instances paired with binary labels corrupted by arbitrary instance- and label-dependent noise. With sufficiently many such samples, can we optimally classify and rank instances with respect to the noise-free distribution? We provide a theoretical analysis of this question, with three main contributions. First, we prove that for instance-dependent noise, any algorithm that is consistent for classification on the noisy distribution is also consistent on the clean distribution. Second, we prove that for a broad class of instance- and label-dependent noise, a similar consistency result holds for the area under the ROC curve. Third, for the latter noise model, when the noise-free class-probability function belongs to the generalised linear model family, we show that the Isotron can efficiently and provably learn from the corrupted sample.