论文信息 - Large margin non-linear embedding

Large margin non-linear embedding

It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, we "learn" the location of the data. This way we (i) do not need a metric (or even stronger structure) - pairwise dissimilarities suffice; and additionally (ii) produce low-dimensional embeddings that can be analyzed visually. We achieve this by combining an entropy-based embedding method with an entropy-based version of semi-supervised logistic regression. We present results for clustering and semi-supervised classification.

Joaquin Quiñonero Candela | Alexander Zien | A. Zien | J. Q. Candela

[1] Mikhail Belkin,et al. Semi-Supervised Learning on Riemannian Manifolds , 2004, Machine Learning.

[2] Heekuck Oh,et al. Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[3] Yoshua Bengio,et al. Semi-supervised Learning by Entropy Minimization , 2004, CAP.

[4] Geoffrey E. Hinton,et al. Stochastic Neighbor Embedding , 2002, NIPS.

[5] Alexander Zien,et al. Semi-Supervised Classification by Low Density Separation , 2005, AISTATS.

[6] Seungjin Choi,et al. Fast stochastic neighbor embedding: a trust-region algorithm , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[7] J. Tenenbaum,et al. A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[8] Teuvo Kohonen,et al. Self-organization and associative memory: 3rd edition , 1989 .

[9] Jianhua Lin,et al. Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[10] S T Roweis,et al. Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[11] Thomas L. Griffiths,et al. Parametric Embedding for Class Visualization , 2004, Neural Computation.

[12] Thorsten Joachims,et al. Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.