Unified Framework for Feature Extraction based on Contrastive Learning

TL;DR

This paper introduces a unified contrastive learning framework for feature extraction that works effectively in both unsupervised and supervised settings, improving performance on real datasets.

Contribution

A novel unified framework for contrastive learning-based feature extraction that integrates unsupervised and supervised methods within a single approach.

Findings

Superior performance on five real datasets

Effective in both unsupervised and supervised scenarios

Introduces three specific contrastive learning methods

Abstract

Feature extraction is an efficient approach for alleviating the issue of dimensionality in high-dimensional data. As a popular self-supervised learning method, contrastive learning has recently garnered considerable attention. In this study, we proposed a unified framework based on a new perspective of contrastive learning (CL) that is suitable for both unsupervised and supervised feature extraction. The proposed framework first constructed two CL graph for uniquely defining the positive and negative pairs. Subsequently, the projection matrix was determined by minimizing the contrastive loss function. In addition, the proposed framework considered both similar and dissimilar samples to unify unsupervised and supervised feature extraction. Moreover, we propose the three specific methods: unsupervised contrastive learning method, supervised contrastive learning method 1 ,and supervised contrastive learning method 2. Finally, the numerical experiments on five real datasets demonstrated the superior performance of the proposed framework in comparison to the existing methods.