A novel multi-label classification algorithm based on -nearest neighbor and random walk
The multi-label classification problem occurs in many real-world tasks where an object is naturally associated with multiple labels, that is, concepts. The integration of the random walk approach in the multi-label classification methods attracts many researchers’ sight. One challenge of using the r...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi - SAGE Publishing
2020-03-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/1550147720911892 |
| _version_ | 1827008589489766400 |
|---|---|
| author | Zhen-Wu Wang Si-Kai Wang Ben-Ting Wan William Wei Song |
| author_facet | Zhen-Wu Wang Si-Kai Wang Ben-Ting Wan William Wei Song |
| author_sort | Zhen-Wu Wang |
| collection | DOAJ |
| description | The multi-label classification problem occurs in many real-world tasks where an object is naturally associated with multiple labels, that is, concepts. The integration of the random walk approach in the multi-label classification methods attracts many researchers’ sight. One challenge of using the random walk-based multi-label classification algorithms is to construct a random walk graph for the multi-label classification algorithms, which may lead to poor classification quality and high algorithm complexity. In this article, we propose a novel multi-label classification algorithm based on the random walk graph and the K -nearest neighbor algorithm (named MLRWKNN). This method constructs the vertices set of a random walk graph for the K -nearest neighbor training samples of certain test data and the edge set of correlations among labels of the training samples, thus considerably reducing the overhead of time and space. The proposed method improves the similarity measurement by differentiating and integrating the discrete and continuous features, which reflect the relationships between instances more accurately. A label predicted method is devised to reduce the subjectivity of the traditional threshold method. The experimental results with four metrics demonstrate that the proposed method outperforms the seven state-of-the-art multi-label classification algorithms in contrast and makes a significant improvement for multi-label classification. |
| first_indexed | 2024-03-12T07:06:07Z |
| format | Article |
| id | doaj.art-574ad079eff84d5b93cee1689696fda9 |
| institution | Directory Open Access Journal |
| issn | 1550-1477 |
| language | English |
| last_indexed | 2025-02-18T12:35:12Z |
| publishDate | 2020-03-01 |
| publisher | Hindawi - SAGE Publishing |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj.art-574ad079eff84d5b93cee1689696fda92024-11-02T04:14:20ZengHindawi - SAGE PublishingInternational Journal of Distributed Sensor Networks1550-14772020-03-011610.1177/1550147720911892A novel multi-label classification algorithm based on -nearest neighbor and random walkZhen-Wu Wang0Si-Kai Wang1Ben-Ting Wan2William Wei Song3Department of Computer Science and Technology, China University of Mining and Technology, Beijing, ChinaDepartment of Computer Science and Technology, China University of Mining and Technology, Beijing, ChinaSchool of Software and Internet of Things Engineering, Jiangxi University of Finance and Economics, Nanchang, ChinaDepartment of Information Systems, Dalarna University, Falun, SwedenThe multi-label classification problem occurs in many real-world tasks where an object is naturally associated with multiple labels, that is, concepts. The integration of the random walk approach in the multi-label classification methods attracts many researchers’ sight. One challenge of using the random walk-based multi-label classification algorithms is to construct a random walk graph for the multi-label classification algorithms, which may lead to poor classification quality and high algorithm complexity. In this article, we propose a novel multi-label classification algorithm based on the random walk graph and the K -nearest neighbor algorithm (named MLRWKNN). This method constructs the vertices set of a random walk graph for the K -nearest neighbor training samples of certain test data and the edge set of correlations among labels of the training samples, thus considerably reducing the overhead of time and space. The proposed method improves the similarity measurement by differentiating and integrating the discrete and continuous features, which reflect the relationships between instances more accurately. A label predicted method is devised to reduce the subjectivity of the traditional threshold method. The experimental results with four metrics demonstrate that the proposed method outperforms the seven state-of-the-art multi-label classification algorithms in contrast and makes a significant improvement for multi-label classification.https://doi.org/10.1177/1550147720911892 |
| spellingShingle | Zhen-Wu Wang Si-Kai Wang Ben-Ting Wan William Wei Song A novel multi-label classification algorithm based on -nearest neighbor and random walk International Journal of Distributed Sensor Networks |
| title | A novel multi-label classification algorithm based on -nearest neighbor and random walk |
| title_full | A novel multi-label classification algorithm based on -nearest neighbor and random walk |
| title_fullStr | A novel multi-label classification algorithm based on -nearest neighbor and random walk |
| title_full_unstemmed | A novel multi-label classification algorithm based on -nearest neighbor and random walk |
| title_short | A novel multi-label classification algorithm based on -nearest neighbor and random walk |
| title_sort | novel multi label classification algorithm based on nearest neighbor and random walk |
| url | https://doi.org/10.1177/1550147720911892 |
| work_keys_str_mv | AT zhenwuwang anovelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT sikaiwang anovelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT bentingwan anovelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT williamweisong anovelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT zhenwuwang novelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT sikaiwang novelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT bentingwan novelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk AT williamweisong novelmultilabelclassificationalgorithmbasedonnearestneighborandrandomwalk |