Label Information Bottleneck for Label Enhancement
Authors:
Preprint
Abstract
In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information contained in the dataset may lead to unsatisfactory recovery performance. To address this limitation, we make efforts to excavate the essential label relevant information to improve the recovery performance. Our method formulates the LE problem as the following two joint processes: 1) learning the representation with the essential label relevant information, 2) recovering label distributions based on the learned representation. The label relevant information can be excavated based on the "bottleneck" formed by the learned representation. Significantly, both the label relevant information about the label assignments and the label relevant information about the label gaps can be explored in our method. Evaluation experiments conducted on several benchmark label distribution learning datasets verify the effectiveness and competitiveness of LIB. Our source codes are available https://github.com/qinghai-zheng/LIBLEKeywords
All Related Versions
This publication has 8 references indexed in Scilit:
- The Emerging Trends of Multi-Label LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Label Enhancement by Maintaining Positive and Negative Label RelationIEEE Transactions on Knowledge and Data Engineering, 2021
- Generalized Label Enhancement with Sample CorrelationsIEEE Transactions on Knowledge and Data Engineering, 2021
- Label Enhancement for Label Distribution LearningIEEE Transactions on Knowledge and Data Engineering, 2019
- Label Distribution Learning with Label Correlations on Local SamplesIEEE Transactions on Knowledge and Data Engineering, 2019
- Indoor Crowd Counting by Mixture of Gaussians Label Distribution LearningIEEE Transactions on Image Processing, 2019
- Age Estimation Using Expectation of Label Distribution Learning2018
- Fuzzy SVM with a new fuzzy membership functionNeural Computing and Applications, 2006