Toward the Analysis of Graph Neural Networks
This addresses the problem of analyzing GNNs for researchers and practitioners, but it is incremental as it adapts existing methods rather than introducing a new paradigm.
The paper tackles the lack of analysis tools for Graph Neural Networks (GNNs) by proposing a method to convert GNNs into Feed Forward Neural Networks (FFNNs), enabling reuse of existing FFNN analyses, as demonstrated in a node classification case study.
Graph Neural Networks (GNNs) have recently emerged as a robust framework for graph-structured data. They have been applied to many problems such as knowledge graph analysis, social networks recommendation, and even Covid19 detection and vaccine developments. However, unlike other deep neural networks such as Feed Forward Neural Networks (FFNNs), few analyses such as verification and property inferences exist, potentially due to dynamic behaviors of GNNs, which can take arbitrary graphs as input, whereas FFNNs which only take fixed size numerical vectors as inputs. This paper proposes an approach to analyze GNNs by converting them into FFNNs and reusing existing FFNNs analyses. We discuss various designs to ensure the scalability and accuracy of the conversions. We illustrate our method on a study case of node classification. We believe that our approach opens new research directions for understanding and analyzing GNNs.