Semi-supervised Learning with Explicit Relationship Regularization

02/11/2016
by   Kwang In Kim, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2021

Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

Twin neural network regression (TNNR) is a semi-supervised regression al...
research
11/08/2021

Can semi-supervised learning reduce the amount of manual labelling required for effective radio galaxy morphology classification?

In this work, we examine the robustness of state-of-the-art semi-supervi...
research
05/17/2023

RelationMatch: Matching In-batch Relationships for Semi-supervised Learning

Semi-supervised learning has achieved notable success by leveraging very...
research
03/23/2022

Semi-Supervised Graph Learning Meets Dimensionality Reduction

Semi-supervised learning (SSL) has recently received increased attention...
research
07/01/2019

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

In the recent years, there is a growing interest in semi-supervised lear...
research
05/07/2021

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

Interpreting deep neural networks from the ordinary differential equatio...
research
10/01/2022

Learning Globally Smooth Functions on Manifolds

Smoothness and low dimensional structures play central roles in improvin...

Please sign up or login with your details

Forgot password? Click here to reset