Multi-label classification via learning a unified object-label graph with sparse representation

Yao, Lina, Sheng, Quan Z., Ngu, Anne H.H., Gao, Byron J., Li, Xue and Wang, Sen (2015) Multi-label classification via learning a unified object-label graph with sparse representation. World Wide Web, 1-25. doi:10.1007/s11280-015-0376-7

Author Yao, Lina
Sheng, Quan Z.
Ngu, Anne H.H.
Gao, Byron J.
Li, Xue
Wang, Sen
Title Multi-label classification via learning a unified object-label graph with sparse representation
Journal name World Wide Web   Check publisher's open access policy
ISSN 1386-145X
Publication date 2015-11-27
Year available 2015
Sub-type Article (original research)
DOI 10.1007/s11280-015-0376-7
Open Access Status Not yet assessed
Start page 1
End page 25
Total pages 25
Place of publication New York, United States
Publisher Springer
Collection year 2016
Language eng
Formatted abstract
Automatic annotation is an essential technique for effectively handling and organizing Web objects (e.g., Web pages), which have experienced an unprecedented growth over the last few years. Automatic annotation is usually formulated as a multi-label classification problem. Unfortunately, labeled data are often time-consuming and expensive to obtain. Web data also accommodate much richer feature space. This calls for new semi-supervised approaches that are less demanding on labeled data to be effective in classification. In this paper, we propose a graph-based semi-supervised learning approach that leverages random walks and ℓ 1 sparse reconstruction on a mixed object-label graph with both attribute and structure information for effective multi-label classification. The mixed graph contains an object-affinity subgraph, a label-correlation subgraph, and object-label edges with adaptive weight assignments indicating the assignment relationships. The object-affinity subgraph is constructed using ℓ 1 sparse graph reconstruction with extracted structural meta-text, while the label-correlation subgraph captures pairwise correlations among labels via linear combination of their co-occurrence similarity and kernel-based similarity. A random walk with adaptive weight assignment is then performed on the constructed mixed graph to infer probabilistic assignment relationships between labels and objects. Extensive experiments on real Yahoo! Web datasets demonstrate the effectiveness of our approach.
Keyword Classification
Multi-label classification
Sparse reconstruction
Random walk with restart
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2016 Collection
School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 15 Dec 2015, 00:26:46 EST by System User on behalf of Scholarly Communication and Digitisation Service