Adaptive Loss Minimization for Semi-Supervised Elastic Embedding
Feiping Nie, Hua Wang, Heng Huang, Chris Ding
IJCAI - 2013
The semi-supervised learning usually only predict labels for unlabeled data appearing in training data, and cannot effectively predict labels for testing data never appearing in training set. To handle this out-of-sample problem, many inductive methods make a constraint such that the predicted label matrix should be exactly equal to a linear model. In practice, this constraint is too rigid to capture the manifold structure of data. Motivated by this deficiency, we relax the rigid linear embedding constraint and propose to use an elastic embedding constraint on the predicted label matrix such that the manifold structure can be better explored. To solve our new objective and also a more general optimization problem, we study a novel adaptive loss with efficient optimization algorithm. Our new adaptive loss minimization method takes the advantages of both L1 norm and L2 norm, and is robust to the data outlier under Laplacian distribution and can efficiently learn the normal data under Gaussian distribution. Experiments have been performed on image classification tasks and our approach outperforms other state-of-the-art methods.
Links
- View publications from Hua Wang
- View publications presented in IJCAI
- View publications researching Embeddings
- View publications researching Robust Learning Models
- View publications applied to Computer Vision
Cite this paper
MLA
Nie, Feiping, et al. "Adaptive loss minimization for semi-supervised elastic embedding." Twenty-Third International Joint Conference on Artificial Intelligence. 2013.
BibTeX
@inproceedings{nie2013adaptive,
title={Adaptive loss minimization for semi-supervised elastic embedding},
author={Nie, Feiping and Wang, Hua and Huang, Heng and Ding, Chris},
booktitle={Twenty-Third International Joint Conference on Artificial Intelligence},
year={2013}
}