A Learned Generalized Geodesic Distance Function-Based Approach for Node Feature Augmentation on Graphs

TL;DR

This paper introduces LGGD, a learned approach for generating node features on graphs using a generalized geodesic distance function, improving robustness and performance in node classification tasks.

Contribution

The paper presents a novel method called LGGD that learns a generalized geodesic distance for node feature augmentation, demonstrating robustness and competitive results.

Findings

Improved node classification accuracy.

Robustness to noise and outliers.

Competitive performance on real-world datasets.

Abstract

Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision. In this work, we introduce an approach called `LGGD' (Learned Generalized Geodesic Distances). This method involves generating node features by learning a generalized geodesic distance function through a training pipeline that incorporates training data, graph topology and the node content features. The strength of this method lies in the proven robustness of the generalized geodesic distances to noise and outliers. Our contributions encompass improved performance in node classification tasks, competitive results with state-of-the-art methods on real-world graph datasets, the demonstration of the learnability of parameters within the generalized geodesic equation on graph, and dynamic inclusion of new labels.