%0 Journal Article %1 bodnar2020graph %A Bodnar, Cristian %A Cangea, Cătălina %A Liò, Pietro %D 2020 %K deep-learning geometry graphs sets topology %T Deep Graph Mapper: Seeing Graphs through the Neural Lens %U http://arxiv.org/abs/2002.03864 %X Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph. However, even though these abstract representations are powerful for downstream tasks, they are not equally suitable for visualisation purposes. In this work, we merge Mapper, an algorithm from the field of Topological Data Analysis (TDA), with the expressive power of Graph Neural Networks (GNNs) to produce hierarchical, topologically-grounded visualisations of graphs. These visualisations do not only help discern the structure of complex graphs but also provide a means of understanding the models applied to them for solving various tasks. We further demonstrate the suitability of Mapper as a topological framework for graph pooling by mathematically proving an equivalence with Min-Cut and Diff Pool. Building upon this framework, we introduce a novel pooling algorithm based on PageRank, which obtains competitive results with state of the art methods on graph classification benchmarks.

@article{bodnar2020graph, abstract = {Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph. However, even though these abstract representations are powerful for downstream tasks, they are not equally suitable for visualisation purposes. In this work, we merge Mapper, an algorithm from the field of Topological Data Analysis (TDA), with the expressive power of Graph Neural Networks (GNNs) to produce hierarchical, topologically-grounded visualisations of graphs. These visualisations do not only help discern the structure of complex graphs but also provide a means of understanding the models applied to them for solving various tasks. We further demonstrate the suitability of Mapper as a topological framework for graph pooling by mathematically proving an equivalence with Min-Cut and Diff Pool. Building upon this framework, we introduce a novel pooling algorithm based on PageRank, which obtains competitive results with state of the art methods on graph classification benchmarks.}, added-at = {2020-02-26T14:12:14.000+0100}, author = {Bodnar, Cristian and Cangea, Cătălina and Liò, Pietro}, biburl = {https://www.bibsonomy.org/bibtex/2d269dc9baad160381a4e1ed8bd962c06/kirk86}, description = {[2002.03864] Deep Graph Mapper: Seeing Graphs through the Neural Lens}, interhash = {d6b3e5c01f0844c2473a053dda9398d8}, intrahash = {d269dc9baad160381a4e1ed8bd962c06}, keywords = {deep-learning geometry graphs sets topology}, note = {cite arxiv:2002.03864Comment: 13 pages, 10 figures}, timestamp = {2020-02-26T14:13:26.000+0100}, title = {Deep Graph Mapper: Seeing Graphs through the Neural Lens}, url = {http://arxiv.org/abs/2002.03864}, year = 2020 }