Name
Abstract | ||
|---|---|---|
Several meta-learning techniques for multi-label classification (MLC), such as chaining and stacking, have already been proposed in the literature, mostly aimed at improving predictive accuracy through the exploitation of label dependencies. In this paper, we propose another technique of that kind, called dependent binary relevance (DBR) learning. DBR combines properties of both, chaining and stacking. We provide a careful analysis of the relationship between these and other techniques, specifically focusing on the underlying dependency structure and the type of training data used for model construction. Moreover, we offer an extensive empirical evaluation, in which we compare different techniques on MLC benchmark data. Our experiments provide evidence for the good performance of DBR in terms of several evaluation measures that are commonly used in MLC. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1016/j.patcog.2013.09.029 | Pattern Recognition |
Keywords | Field | DocType |
different technique,training data,dependent binary relevance,extensive empirical evaluation,evaluation measure,dependent binary relevance model,good performance,mlc benchmark data,multi-label classification,label dependency,careful analysis,meta-learning technique,stacking,chaining | Training set,Data mining,Chaining,Computer science,Multi-label classification,Dependency structure,Exploit,Artificial intelligence,Classifier (linguistics),Machine learning,Binary number,Stacking | Journal |
Volume | Issue | ISSN |
47 | 3 | 0031-3203 |
Citations | PageRank | References |
30 | 0.83 | 21 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Elena Montanes | 1 | 168 | 15.24 |
| Robin Senge | 2 | 151 | 8.43 |
| Jose Barranquero | 3 | 119 | 4.25 |
| José Ramón Quevedo | 4 | 175 | 15.37 |
| Juan José Del Coz | 5 | 312 | 22.86 |
| Eyke Hüllermeier | 6 | 3423 | 213.52 |