Dimensionality Reduction by Learning an Invariant Mapping

Citations Over TimeTop 1% of 2006 papers

Abstract

Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that 'similar" points in input space are mapped to nearby points on the manifold. We present a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. The learning relies solely on neighborhood relationships and does not require any distancemeasure in the input space. The method can learn mappings that are invariant to certain transformations of the inputs, as is demonstrated with a number of experiments. Comparisons are made to other techniques, in particular LLE.

Related Papers

• Overview of nonlinear dimensionality reduction methods in manifold learning(2007)
• Manifold learning and manifold alignment based on coupled linear projections(2010)
• → Multiple Manifold Learning by Nonlinear Dimensionality Reduction(2011)10 cited
• → A Fast Manifold Learning Algorithm for Dimensionality Reduction(2016)1 cited
• → Framework of Multiple-point Statistical Simulation Using Manifold Learning for the Dimensionality Reduction of Patterns(2020)