Semi-Supervised Learning with Bidirectional Adaptive Pairwise Encoding

Abstract

In contrast to classic supervised learning methods that demand pre-defined class labels, pairwise encoding or side-information encoding merely requires pairwise similarity information to drive feature learning, which makes it very appealing for many fundamental tasks such as dimensionality reduction and semi-supervised learning. In this paper, we present a novel bimarginal pairwise encoding model, along with deep autoencoder, to learn nonlinear embedding for the aforementioned tasks. The new method learns powerful features that preserve critical pairwise information in a semi-supervised manner. It has achieved better performance on the well-known yet hard to make improvement benchmark MINIST compared with other methods in the same category, i.e. Autoencoder [4], Invariant Mapping for Dimensionality Reduction [1], Neighborhood Component Analysis [3], and Fixed Bi-Margin Pairwise Encoding [11].