Topological Graph Neural Networks
arXiv:2102.07835
Abstract
Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks, yet have been shown to be oblivious to eminent substructures such as cycles. We present TOGL, a novel layer that incorporates global topological information of a graph using persistent homology. TOGL can be easily integrated into any type of GNN and is strictly more expressive (in terms the Weisfeiler--Lehman graph isomorphism test) than message-passing GNNs. Augmenting GNNs with TOGL leads to improved predictive performance for graph and node classification tasks, both on synthetic data sets, which can be classified by humans using their topology but not by ordinary GNNs, and on real-world data.
References in corpus (14)
- Fast Graph Representation Learning with PyTorch Geometric
- A Survey on Graph Kernels
- TUDataset: A collection of benchmark datasets for learning with graphs
- Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- Residual Gated Graph ConvNets
- Benchmarking Graph Neural Networks
- On Valid Optimal Assignment Kernels and Applications to Graph Classification
- Graph Kernels: A Survey
- Learning metrics for persistence-based summaries and applications for graph classification
- Computing Multidimensional Persistence
- Can Graph Neural Networks Count Substructures?
- Continuation of Point Clouds via Persistence Diagrams
- Stabilizing the unstable output of persistent homology computations
- PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction