paper-with-me

Papers

Learning from Binary Labels with Instance-Dependent Corruption

2016-05-03 · Aditya Krishna Menon, Brendan van Rooyen, Nagarajan Natarajan

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.

📄 PDF Abstract BibTeX arXiv:1605.00751

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Benchmarking Instance-Dependent Label Noise with Controlled Corruptions

2026-06-12 · Shadman Islam, Agustinus Kristiadi, Mostafa Milani arxiv

Synthetic instance-dependent label noise (IDN) benchmarks are widely used to evaluate noisy-label learning methods, yet existing approaches typically generate noise through imperfect annotators or classifier raters, leav…

Data Imputation through the Identification of Local Anomalies

2014-09-30 · Huseyin Ozkan, Ozgun S. Pelvan, Suleyman S. Kozat

We introduce a comprehensive and statistical framework in a model free setting for a complete treatment of localized data corruptions due to severe noise sources, e.g., an occluder in the case of a visual recording. With…

Imputation

Binary classification with corrupted labels

2021-06-16 · Yonghoon Lee, Rina Foygel Barber

In a binary classification problem where the goal is to fit an accurate predictor, the presence of corrupted labels in the training data set may create an additional challenge. However, in settings where likelihood maxim…

Binary ClassificationClassification

Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark

2025-06-14 · Suyeon Kim, SeongKu Kang, Dongwoo Kim, Jungseul Ok 외

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification tasks but struggle with label noise in real-world data. Existing studies on graph learning with label noise commonly rely on …

BenchmarkingGraph LearningNode Classification

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

2021-01-14 · Qizhou Wang, Bo Han, Tongliang Liu, Gang Niu 외

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learn…