Graph Neural Networks

Recommender systems are vital to online platforms, with Graph Neural Network (GNN) approaches showing excellent accuracy. However, beyond-accuracy metrics like diversity, serendipity, and fairness significantly impact user satisfaction. This review examines these dimensions in GNN-based recommenders, analyzing recent developments that balance accuracy with these broader objectives. We explore how various model development stages—from data preprocessing to training methodologies—affect these metrics. The paper addresses practical challenges in maintaining high accuracy while enhancing diversity, serendipity, and fairness, and outlines future research directions for more holistic GNN-based recommender systems. Our contribution lies in providing a comprehensive understanding of the multidimensional considerations essential to effective recommender system design.

This study investigates how community structure and homophily influence Graph Neural Networks (GNNs) in semi-supervised node classification tasks. By systematically modifying eight datasets and measuring GNN performance with and without these structural properties, we demonstrate their significant impact on classification accuracy and reveal insights about their interaction. We introduce an information-theoretic metric to quantify community-label correlation, providing practical guidelines for model selection based on graph structure. Our findings enhance understanding of GNN capabilities and improve model selection for semi-supervised node classification tasks.

Graph neural networks (GNNs) are vulnerable to adversarial attacks, but most attack methods require node attribute information. This paper introduces Structack, an uninformed attack strategy that exploits only graph structural properties without needing node attributes. By targeting links between nodes with low similarity and low centrality, Structack approaches the effectiveness of informed attacks while being computationally more efficient. The findings demonstrate that structural knowledge alone can significantly degrade GNN performance, contributing to the development of more robust graph-based machine learning methods.

This study examines how community structures in graphs affect Graph Neural Networks (GNNs) in node classification tasks. Through experiments on six datasets, researchers found that community structures significantly impact GNN performance. When nodes in a community mostly share the same label, disrupting the community structure dramatically reduces performance. Conversely, when labels don’t correlate with communities, graph structure becomes less relevant and simple feature-based models perform comparably. The research provides insights and guidelines for selecting appropriate models based on graph structure characteristics.

Research module developing privacy-preserving, verifiable, and explainable AI solutions, combining cryptography, explainable AI, and machine learning, contributing to both academic knowledge and practical industry applications.