Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

by   Pengfei Chen, et al.

Supervised learning under label noise has seen numerous advances recently, while existing theoretical findings and empirical results broadly build up on the class-conditional noise (CCN) assumption that the noise is independent of input features given the true label. In this work, we present a theoretical hypothesis testing and prove that noise in real-world dataset is unlikely to be CCN, which confirms that label noise should depend on the instance and justifies the urgent need to go beyond the CCN assumption.The theoretical results motivate us to study the more general and practical-relevant instance-dependent noise (IDN). To stimulate the development of theory and methodology on IDN, we formalize an algorithm to generate controllable IDN and present both theoretical and empirical evidence to show that IDN is semantically meaningful and challenging. As a primary attempt to combat IDN, we present a tiny algorithm termed self-evolution average label (SEAL), which not only stands out under IDN with various noise fractions, but also improves the generalization on real-world noise benchmark Clothing1M. Our code is released. Notably, our theoretical analysis in Section 2 provides rigorous motivations for studying IDN, which is an important topic that deserves more research attention in future.



There are no comments yet.


page 1

page 6

page 10


Confidence Scores Make Instance-dependent Label-noise Learning Possible

Learning with noisy labels has drawn a lot of attention. In this area, m...

Statistical Hypothesis Testing for Class-Conditional Label Noise

In this work we aim to provide machine learning practitioners with tools...

Approximating Instance-Dependent Noise via Instance-Confidence Embedding

Label noise in multiclass classification is a major obstacle to the depl...

Parts-dependent Label Noise: Towards Instance-dependent Label Noise

Learning with the instance-dependent label noise is challenging, because...

Learning with Instance-Dependent Label Noise: A Sample Sieve Approach

Human-annotated labels are often prone to noise, and the presence of suc...

How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?

Incorrectly labeled examples, or label noise, is common in real-world co...

Diagnostic checking in FARIMA models with uncorrelated but non-independent error terms

This work considers the problem of modified portmanteau tests for testin...

Code Repositories


Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.