Name
Abstract | ||
|---|---|---|
Multi-label learning arises in many real-world tasks where an object is naturally associated with multiple concepts. It is well-accepted that, in order to achieve a good performance, the relationship among labels should be exploited. Most existing approaches require the label relationship as prior knowledge, or exploit by counting the label co-occurrence. In this paper, we propose the MAHR approach, which is able to automatically discover and exploit label relationship. Our basic idea is that, if two labels are related, the hypothesis generated for one label can be helpful for the other label. MAHR implements the idea as a boosting approach with a hypothesis reuse mechanism. In each boosting round, the base learner for a label is generated by not only learning on its own task but also reusing the hypotheses from other labels, and the amount of reuse across labels provides an estimate of the label relationship. Extensive experimental results validate that MAHR is able to achieve superior performance and discover reasonable label relationship. Moreover, we disclose that the label relationship is usually asymmetric. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1145/2339530.2339615 | KDD |
Keywords | Field | DocType |
label relationship,basic idea,multi-label hypothesis reuse,label co-occurrence,reasonable label relationship,good performance,existing approach,multi-label learning,mahr approach,hypothesis reuse mechanism,superior performance | Data mining,Reuse,Computer science,Multi label learning,Exploit,Boosting (machine learning),Artificial intelligence,Machine learning | Conference |
Citations | PageRank | References |
15 | 0.61 | 24 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sheng-Jun Huang | 1 | 475 | 27.21 |
| Yang Yu | 2 | 488 | 48.20 |
| Zhi-Hua Zhou | 3 | 13480 | 569.92 |