Key Principles of Graph Machine Learning: Representation, Robustness, and Generalization

TL;DR

This paper explores the core principles of Graph Neural Networks, focusing on improving their representation learning, robustness to adversarial attacks, and generalization capabilities through novel techniques and theoretical insights.

Contribution

It introduces new GNN techniques based on Graph Shift Operators, data augmentation for better generalization, and orthonormalization methods for increased robustness.

Findings

Enhanced GNN performance with GSOs

Improved generalization via graph data augmentation

Increased robustness through orthonormalization and noise defenses

Abstract

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations from structured data. Despite their growing popularity and success across various applications, GNNs encounter several challenges that limit their performance. in their generalization, robustness to adversarial perturbations, and the effectiveness of their representation learning capabilities. In this dissertation, I investigate these core aspects through three main contributions: (1) developing new representation learning techniques based on Graph Shift Operators (GSOs, aiming for enhanced performance across various contexts and applications, (2) introducing generalization-enhancing methods through graph data augmentation, and (3) developing more robust GNNs by leveraging orthonormalization techniques and noise-based defenses against adversarial attacks. By addressing these challenges, my work provides a more principled understanding of the limitations and potential of GNNs.