Trustworthy Graph Neural Networks: Aspects, Methods and Trends

TL;DR

This paper surveys the development of trustworthy graph neural networks, emphasizing six key aspects—robustness, explainability, privacy, fairness, accountability, and environmental impact—and discusses their interrelations and future research directions.

Contribution

It provides a comprehensive roadmap and summary of existing efforts to enhance trustworthiness in GNNs across multiple aspects and highlights future trends for research and industrial application.

Findings

Summarizes efforts across six trustworthiness aspects.

Highlights cross-aspect relationships in GNNs.

Outlines future research directions for trustworthy GNNs.

Abstract

Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such as drug discovery in life sciences and n-body simulation in astrophysics. However, task performance is not the only requirement for GNNs. Performance-oriented GNNs have exhibited potential adverse effects like vulnerability to adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption in edge computing environments. To avoid these unintentional harms, it is necessary to build competent GNNs characterised by trustworthiness. To this end, we propose a comprehensive roadmap to build trustworthy GNNs from the view of the various computing technologies involved. In this survey, we introduce basic concepts and comprehensively summarise existing efforts for trustworthy GNNs from six aspects, including robustness, explainability, privacy, fairness, accountability, and environmental well-being. Additionally, we highlight the intricate cross-aspect relations between the above six aspects of trustworthy GNNs. Finally, we present a thorough overview of trending directions for facilitating the research and industrialisation of trustworthy GNNs.