Graph Neural Networks (GNNs) have gained popularity in various fields, such as recommendation systems, social network analysis and fraud detection. However, despite their effectiveness, the topological nature of GNNs makes it challenging for users to understand the model predictions. To address this challenge, we built a user-friendly UI to visualize the most important relationships for both homogeneous and heterogeneous static graphs models, which a post-hoc explanation technique called GNNExplainer is implemented. This UI can be applied to a wide range of applications that use graph models. It offers an intuitive and interpretable way for users to understand the complex relationships within a graph and how they influence the model’s predictions.
Research areas
