CLRGaze: Contrastive Learning of Representations for Eye Movement Signals

TL;DR

This paper introduces CLRGaze, a contrastive learning method for self-supervised feature extraction from eye movement signals, achieving high accuracy in biometric tasks across diverse datasets.

Contribution

It presents a novel contrastive learning approach with data transformations for eye movement signals, enabling effective feature learning without manual feature engineering.

Findings

Achieved 84.6% accuracy on a mixed dataset using linear classification.

Reaching up to 97.3% accuracy on individual datasets.

Demonstrated generalization of the method across different data conditions.

Abstract

Eye movements are intricate and dynamic biosignals that contain a wealth of cognitive information about the subject. However, these are ambiguous signals and therefore require meticulous feature engineering to be used by machine learning algorithms. We instead propose to learn feature vectors of eye movements in a self-supervised manner. We adopt a contrastive learning approach and propose a set of data transformations that encourage a deep neural network to discern salient and granular gaze patterns. This paper presents a novel experiment utilizing six eye-tracking data sets despite different data specifications and experimental conditions. We assess the learned features on biometric tasks with only a linear classifier, achieving 84.6% accuracy on a mixed dataset, and up to 97.3% accuracy on a single dataset. Our work advances the state of machine learning for eye movements and provides insights into a general representation learning method not only for eye movements but also for similar biosignals.