Deep Graph Mapper: Seeing Graphs through the Neural Lens
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.
Code (1)
Tasks
Graph ClassificationGraph Representation LearningRepresentation LearningTopological Data AnalysisSimilar Papers 제목 키워드 기반
Hotspot identification for Mapper graphs
Mapper algorithm can be used to build graph-based representations of high-dimensional data capturing structurally interesting features such as loops, flares or clusters. The graph can be further annotated with additional…
Improving Mapper's Robustness by Varying Resolution According to Lens-Space Density
We propose a modification of the Mapper algorithm that removes the assumption of a single resolution scale across semantic space and improves the robustness of the results under change of parameters. Our work is motivate…
Mapper-GIN: Lightweight Structural Graph Abstraction for Corrupted 3D Point Cloud Classification
Robust 3D point cloud classification is often pursued by scaling up backbones or relying on specialized data augmentation. We instead ask whether structural abstraction alone can improve robustness, and study a simple to…
3D Point Cloud ClassificationGraph ClassificationData AugmentationStability of Mapper Graph Invariants
Mapper summarizes a large dataset with a smaller graph, which is useful for identifying patterns. However, the Mapper graph may vary widely over different datasets drawn from the same real-world data distribution. In ord…
Mapper Comparison with Wasserstein Metrics
The challenge of describing model drift is an open question in unsupervised learning. It can be difficult to evaluate at what point an unsupervised model has deviated beyond what would be expected from a different sample…
Anomaly DetectionOpen-Ended Question AnsweringTopological Data Analysis