Landmark Alternating Diffusion

TL;DR

This paper introduces Landmark Alternating Diffusion (LAD), a computationally efficient variation of the AD algorithm, supported by theoretical analysis and applied to sleep stage annotation using EEG data.

Contribution

It proposes LAD, a new scalable diffusion algorithm inspired by landmark diffusion, with theoretical analysis and practical application to EEG sleep stage classification.

Findings

LAD offers superior computational efficiency over traditional AD.

Theoretical analysis confirms LAD's effectiveness under manifold assumptions.

LAD successfully applied to EEG sleep stage annotation.

Abstract

Alternating Diffusion (AD) is a commonly applied diffusion-based sensor fusion algorithm. While it has been successfully applied to various problems, its computational burden remains a limitation. Inspired by the landmark diffusion idea considered in the Robust and Scalable Embedding via Landmark Diffusion (ROSELAND), we propose a variation of AD, called Landmark AD (LAD), which captures the essence of AD while offering superior computational efficiency. We provide a series of theoretical analyses of LAD under the manifold setup and apply it to the automatic sleep stage annotation problem with two electroencephalogram channels to demonstrate its application.