Privacy and Transparency in Graph Machine Learning: A Unified Perspective

Understand

Graph Machine Learning (GraphML), whereby classical machine learning is generalized to irregular graph domains, has enjoyed a recent renaissance, leading to a dizzying array of models and their applications in several domains.

• With its growing applicability to sensitive domains and regulations by governmental agencies for trustworthy AI systems, researchers have started looking into the issues of transparency and privacy of graph learning.
• However, these topics have been mainly investigated independently.
• In this position paper, we provide a unified perspective on the interplay of privacy and transparency in GraphML.