Multi-view mid fusion: a universal approach for learning in an HDLSS setting

TL;DR

This paper proposes a universal multi-view mid fusion approach for high-dimensional low-sample-size (HDLSS) learning, demonstrating its effectiveness across various models and tasks by constructing multiple views from high-dimensional data.

Contribution

It introduces three view construction methods for HDLSS data and validates their effectiveness, establishing a foundation for universal multi-view mid fusion learning.

Findings

Effective across multiple models and tasks

Constructs multiple views from high-dimensional data

Generalizes well in HDLSS settings

Abstract

The high-dimensional low-sample-size (HDLSS) setting presents significant challenges in various applications where the feature dimension far exceeds the number of available samples. This paper introduces a universal approach for learning in HDLSS setting using multi-view mid fusion techniques. It shows how existing mid fusion multi-view methods perform well in an HDLSS setting even if no inherent views are provided. Three view construction methods are proposed that split the high-dimensional feature vectors into smaller subsets, each representing a different view. Extensive experimental validation across model-types and learning tasks confirm the effectiveness and generalization of the approach. We believe the work in this paper lays the foundation for further research into the universal benefits of multi-view mid fusion learning.