Privacy and Transparency in Graph Machine Learning: A Unified Perspective
This is an incremental position paper that identifies a gap in research for trustworthy AI systems in sensitive domains, without presenting new methods or results.
The paper tackles the lack of integrated study of privacy and transparency in Graph Machine Learning (GraphML), proposing a unified perspective to address their interplay and outlining challenges and research directions for formal investigation of tradeoffs.
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. In particular, we describe the challenges and possible research directions for a formal investigation of privacy-transparency tradeoffs in GraphML.