Global and local multi-view multi-label learning with incomplete views and labels
- PDF / 2,045,650 Bytes
- 22 Pages / 595.276 x 790.866 pts Page_size
- 66 Downloads / 261 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Global and local multi-view multi-label learning with incomplete views and labels Changming Zhu1 • Panhong Wang1 • Lin Ma1 • Rigui Zhou1 • Lai Wei1 Received: 5 October 2019 / Accepted: 14 March 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Multi-view multi-label learning is widely used in multiple fields, and it aims to process data sets represented by multiple forms (views) and labeled by multiple classes. But most real-world data sets maybe loss some labels and views due to lack of manpower and equipment failure and this causes some difficulties in processing data sets. In this paper, we develop a global and local multi-view multi-label learning with incomplete views and labels (GLMVML-IVL) to process this. In GLMVML-IVL, the usage of label-specific features indicates that class label is determined by some specific features rather than all features; global and local label correlations are taken into consideration with clustering technology; the construction of the pseudo-class label matrix offsets the defect of missing (partial) labels; the adoption of low-rank assumption matrix restores incomplete views; a consensus multi-view representation is put to use to encode the complementary information from different views; the regularizer imposed on label matrix reflects the partial pairwise constraints. Different from traditional methods, this is the first attempt to design a multi-view multi-label learning method with incomplete views and labels by the learning of label-specific features, pseudo-class label matrix, low-rank assumption matrix, global and local label correlations, complementary information, and regularizer imposed on label matrix. Experimental results validate that GLMVML-IVL improves the performance of traditional multi-view multi-label learning methods in statistical and achieves a better performance. Keywords Incomplete views and labels Label-specific features Label correlation Partial pairwise constraints
1 Introduction 1.1 What are multi-view multi-label data sets Multi-label, multi-view, and multi-view multi-label data sets are three data sets which are widely encountered in real-world applications [1–7]. In a multi-label data set, each instance can be labeled with multiple classes. Some classical cases include a scene image which is annotated with several tags [8, 9], a document which may belong to multiple topics [10], and a piece of music which may be associated with different genres [11]. Take Fig. 1 as an instance. There is a data set, and it has two scene images (instances). Each instance can & Changming Zhu [email protected] 1
College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China
be labeled with four tags (class labels), namely nature, landscape, history, and oil painting. We use ‘1’ which indicates that the instance belongs to the corresponding class while ‘0’ indicates the case of not belonging. Then, for the left instance, it is an oil painting about
Data Loading...
