Joint ranking SVM and binary relevance with robust low-rank learning for multi-label classification

DOI10.1016/J.NEUNET.2019.10.002zbMATH Open1434.68474arXiv1911.01658OpenAlexW2981142240WikidataQ91057250 ScholiaQ91057250MaRDI QIDQ2185679FDOQ2185679

Yingjie Tian, Ruobing Zheng, Dalian Liu, Guoqiang Wu

Publication date: 5 June 2020

Published in: Neural Networks (Search for Journal in Brave)

Abstract: Multi-label classification studies the task where each example belongs to multiple labels simultaneously. As a representative method, Ranking Support Vector Machine (Rank-SVM) aims to minimize the Ranking Loss and can also mitigate the negative influence of the class-imbalance issue. However, due to its stacking-style way for thresholding, it may suffer error accumulation and thus reduces the final classification performance. Binary Relevance (BR) is another typical method, which aims to minimize the Hamming Loss and only needs one-step learning. Nevertheless, it might have the class-imbalance issue and does not take into account label correlations. To address the above issues, we propose a novel multi-label classification model, which joints Ranking support vector machine and Binary Relevance with robust Low-rank learning (RBRL). RBRL inherits the ranking loss minimization advantages of Rank-SVM, and thus overcomes the disadvantages of BR suffering the class-imbalance issue and ignoring the label correlations. Meanwhile, it utilizes the hamming loss minimization and one-step learning advantages of BR, and thus tackles the disadvantages of Rank-SVM including another thresholding learning step. Besides, a low-rank constraint is utilized to further exploit high-order label correlations under the assumption of low dimensional label space. Furthermore, to achieve nonlinear multi-label classifiers, we derive the kernelization RBRL. Two accelerated proximal gradient methods (APG) are used to solve the optimization problems efficiently. Extensive comparative experiments with several state-of-the-art methods illustrate a highly competitive or superior performance of our method RBRL.

Full work available at URL: https://arxiv.org/abs/1911.01658

zbMATH Keywords

kernel methodsmulti-label classificationbinary relevancerank-SVMrobust low-rank learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Smooth minimization of non-smooth functions
• A Singular Value Thresholding Algorithm for Matrix Completion
• Understanding Machine Learning
• BoosTexter: A boosting-based system for text categorization
• Convex multi-task feature learning
• Online Learning with Kernels
• ML-KNN: A lazy learning approach to multi-label learning
• Multilabel classification via calibrated label ranking
• Local Rademacher Complexity for Multi-Label Learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (3)

• Multiple kernel learning for label relation and class imbalance in multi-label learning
• A stacking weighted \(k\)-nearest neighbour with thresholding
• Reduced-rank multi-label classification

Uses Software

• LIBSVM
• LIBLINEAR
• MULAN
• BoosTexter
• ML-KNN
• CNN-RNN

This page was built for publication: Joint ranking SVM and binary relevance with robust low-rank learning for multi-label classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2185679)