Multi-Label Noise Transition Matrix Estimation with Label Correlations:
Theory and Algorithm
- URL: http://arxiv.org/abs/2309.12706v1
- Date: Fri, 22 Sep 2023 08:35:38 GMT
- Title: Multi-Label Noise Transition Matrix Estimation with Label Correlations:
Theory and Algorithm
- Authors: Shikun Li, Xiaobo Xia, Hansong Zhang, Shiming Ge, Tongliang Liu
- Abstract summary: Noisy multi-label learning has garnered increasing attention due to the challenges posed by collecting large-scale accurate labels.
The introduction of transition matrices can help model multi-label noise and enable the development of statistically consistent algorithms.
We propose a novel estimator that leverages label correlations without the need for anchor points or precise fitting of noisy class posteriors.
- Score: 73.94839250910977
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Noisy multi-label learning has garnered increasing attention due to the
challenges posed by collecting large-scale accurate labels, making noisy labels
a more practical alternative. Motivated by noisy multi-class learning, the
introduction of transition matrices can help model multi-label noise and enable
the development of statistically consistent algorithms for noisy multi-label
learning. However, estimating multi-label noise transition matrices remains a
challenging task, as most existing estimators in noisy multi-class learning
rely on anchor points and accurate fitting of noisy class posteriors, which is
hard to satisfy in noisy multi-label learning. In this paper, we address this
problem by first investigating the identifiability of class-dependent
transition matrices in noisy multi-label learning. Building upon the
identifiability results, we propose a novel estimator that leverages label
correlations without the need for anchor points or precise fitting of noisy
class posteriors. Specifically, we first estimate the occurrence probability of
two noisy labels to capture noisy label correlations. Subsequently, we employ
sample selection techniques to extract information implying clean label
correlations, which are then used to estimate the occurrence probability of one
noisy label when a certain clean label appears. By exploiting the mismatches in
label correlations implied by these occurrence probabilities, we demonstrate
that the transition matrix becomes identifiable and can be acquired by solving
a bilinear decomposition problem. Theoretically, we establish an estimation
error bound for our multi-label transition matrix estimator and derive a
generalization error bound for our statistically consistent algorithm.
Empirically, we validate the effectiveness of our estimator in estimating
multi-label noise transition matrices, leading to excellent classification
performance.
Related papers
- Rethinking the Value of Labels for Instance-Dependent Label Noise
Learning [43.481591776038144]
noisy labels in real-world applications often depend on both the true label and the features.
In this work, we tackle instance-dependent label noise with a novel deep generative model that avoids explicitly modeling the noise transition matrix.
Our algorithm leverages casual representation learning and simultaneously identifies the high-level content and style latent factors from the data.
arXiv Detail & Related papers (2023-05-10T15:29:07Z) - Clusterability as an Alternative to Anchor Points When Learning with
Noisy Labels [7.920797564912219]
We propose an efficient estimation procedure based on a clusterability condition.
Compared with methods using anchor points, our approach uses substantially more instances and benefits from a much better sample complexity.
arXiv Detail & Related papers (2021-02-10T07:22:56Z) - Learning Noise Transition Matrix from Only Noisy Labels via Total
Variation Regularization [88.91872713134342]
We propose a theoretically grounded method that can estimate the noise transition matrix and learn a classifier simultaneously.
We show the effectiveness of the proposed method through experiments on benchmark and real-world datasets.
arXiv Detail & Related papers (2021-02-04T05:09:18Z) - Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels [86.5943044285146]
The label noise transition matrix $T$ reflects the probabilities that true labels flip into noisy ones.
In this paper, we focus on learning under the mixed closed-set and open-set label noise.
Our method can better model the mixed label noise, following its more robust performance than the prior state-of-the-art label-noise learning methods.
arXiv Detail & Related papers (2020-12-02T02:42:45Z) - Dual T: Reducing Estimation Error for Transition Matrix in Label-noise
Learning [157.2709657207203]
Existing methods for estimating the transition matrix rely heavily on estimating the noisy class posterior.
We introduce an intermediate class to avoid directly estimating the noisy class posterior.
By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices.
arXiv Detail & Related papers (2020-06-14T05:48:20Z) - Meta Transition Adaptation for Robust Deep Learning with Noisy Labels [61.8970957519509]
This study proposes a new meta-transition-learning strategy for the task.
Specifically, through the sound guidance of a small set of meta data with clean labels, the noise transition matrix and the classifier parameters can be mutually ameliorated.
Our method can more accurately extract the transition matrix, naturally following its more robust performance than prior arts.
arXiv Detail & Related papers (2020-06-10T07:27:25Z) - Multi-Class Classification from Noisy-Similarity-Labeled Data [98.13491369929798]
We propose a method for learning from only noisy-similarity-labeled data.
We use a noise transition matrix to bridge the class-posterior probability between clean and noisy data.
We build a novel learning system which can assign noise-free class labels for instances.
arXiv Detail & Related papers (2020-02-16T05:10:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.