Deep Graph Mapper: Seeing Graphs Through the Neural Lens

Graph summarization has received much attention lately, with various works tackling the challenge of defining pooling operators on data regions arbitrary structures. These contrast grid-like ones encountered in image inputs, where techniques such as max-pooling have been enough to show empirical success. In this work, we merge Mapper algorithm expressive power graph neural networks produce topologically grounded summaries. We demonstrate suitability a topological framework for by proving that is generalization methods based soft cluster assignments. Building upon this, how easy it design novel algorithms obtain competitive results other state-of-the-art methods. Additionally, use our method GNN-aided visualisations attributed complex networks.