DeepAI AI Chat
Log In Sign Up

Semi-supervised Learning with Explicit Relationship Regularization

by   Kwang In Kim, et al.

In many learning tasks, the structure of the target space of a function holds rich information about the relationships between evaluations of functions on different data points. Existing approaches attempt to exploit this relationship information implicitly by enforcing smoothness on function evaluations only. However, what happens if we explicitly regularize the relationships between function evaluations? Inspired by homophily, we regularize based on a smooth relationship function, either defined from the data or with labels. In experiments, we demonstrate that this significantly improves the performance of state-of-the-art algorithms in semi-supervised classification and in spectral data embedding for constrained clustering and dimensionality reduction.


page 1

page 2

page 3

page 4


Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

Twin neural network regression (TNNR) is a semi-supervised regression al...

Semi-Supervised Graph Learning Meets Dimensionality Reduction

Semi-supervised learning (SSL) has recently received increased attention...

Adversarial Transformations for Semi-Supervised Learning

We propose a Regularization framework based on Adversarial Transformatio...

A Semi-Supervised Self-Organizing Map with Adaptive Local Thresholds

In the recent years, there is a growing interest in semi-supervised lear...

Diff-ResNets for Few-shot Learning – an ODE Perspective

Interpreting deep neural networks from the ordinary differential equatio...

A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm

Unsupervised embedding learning aims to extract good representation from...