Partial Label Learning Based on Disambiguation Correction Net With Graph Representation
- 31 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (8) , 4953-4967
Abstract
Partial Label Learning (PLL) is a weakly supervised learning framework where each training instance is associated with more than one candidate label. This learning method is dedicated to finding out the true label for each training instance. Most of the current PLL algorithms directly disambiguate the candidate labels without correcting the disambiguated results, making the algorithms vulnerable to the influence of instances easily misjudged. In this paper, GraphDCN, an innovative disambiguation correction net with inductive graph representation learning model is proposed. GraphDCN consists of a disambiguation model and a correction model. For a given instance, the disambiguation model tries to fit its underlying ground-truth label through the candidate label distribution of the instances connected with the given one, while the correction model tries to maximize the distance between the disambiguated labels and non-candidate labels, and uses the label probability thresholds to correct the disambiguated labels that may be wrong. As the training goes on, both the disambiguation and correction models alternately and iteratively boost their performance. Moreover, when considering the implementation of the disambiguation model, a partial cross entropy formulation is proposed to estimate the ground-truth label loss by updating the ambiguity confidence matrix, which can be proved satisfying convergence in PLL. Simulation results reveal the overwhelming performance of GraphDCN.Keywords
Funding Information
- Key Program of the Ministry of Science and Technology (2018YFB1702703)
This publication has 23 references indexed in Scilit:
- Disambiguation-Free Partial Label LearningIEEE Transactions on Knowledge and Data Engineering, 2017
- Mining Fashion Outfit Composition Using an End-to-End Deep Learning Approach on Set DataIEEE Transactions on Multimedia, 2017
- Maximum margin partial label learningMachine Learning, 2016
- Partial Label Learning via Feature-Aware Disambiguation2016
- Weakly Semi-Supervised Deep Learning for Multi-Label Image AnnotationIEEE Transactions on Big Data, 2015
- An Overview of Research Activities in Facial Age Estimation Using the FG-NET Aging Database2015
- Learning by Associating Ambiguously Labeled Images2013
- Dictionary Learning from Ambiguously Labeled Data2013
- Overlapping community detection at scale2013
- Learning from partially supervised data using mixture models and belief functionsPattern Recognition, 2009