Title | ||
---|---|---|
A Novel Regularization Learning for Single-View Patterns: Multi-View Discriminative Regularization |
Abstract | ||
---|---|---|
The existing Multi-View Learning (MVL) is to discuss how to learn from patterns with multiple information sources and has been proven its superior generalization to the usual Single-View Learning (SVL). However, in most real-world cases there are just single source patterns available such that the existing MVL cannot work. The purpose of this paper is to develop a new multi-view regularization learning for single source patterns. Concretely, for the given single source patterns, we first map them into M feature spaces by M different empirical kernels, then associate each generated feature space with our previous proposed Discriminative Regularization (DR), and finally synthesize M DRs into one single learning process so as to get a new Multi-view Discriminative Regularization (MVDR), where each DR can be taken as one view of the proposed MVDR. The proposed method achieves: (1) the complementarity for multiple views generated from single source patterns; (2) an analytic solution for classification; (3) a direct optimization formulation for multi-class problems without one-against-all or one-against-one strategies. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/s11063-010-9132-2 | Neural Processing Letters |
Keywords | Field | DocType |
Discriminative Regularization,Multi-View Learning,Single source patterns,Multi-class problem,Classification | Complementarity (molecular biology),Feature vector,Pattern recognition,Regularization (mathematics),Artificial intelligence,Analytic solution,Discriminative model,Machine learning,Mathematics | Journal |
Volume | Issue | ISSN |
31 | 3 | 1370-4621 |
Citations | PageRank | References |
5 | 0.42 | 37 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhe Wang | 1 | 268 | 18.89 |
Songcan Chen | 2 | 4148 | 191.89 |
Hui Xue | 3 | 227 | 19.14 |
ZhiSong Pan | 4 | 73 | 20.41 |