- Keywords: graph neural networks, graph topology
- TL;DR: Graph neural networks can't reliably detect triangle structures in a graph
- Abstract: Most graph neural network architectures work by message-passing node vector embeddings over the adjacency matrix, and it is assumed that they capture graph topology by doing that. We design two synthetic tasks, focusing purely on topological problems -- triangle detection and clique distance -- on which graph neural networks perform surprisingly badly, failing to detect those "bermuda" triangles. Datasets and their generation scripts are available on https://github.com/FujitsuLaboratories/bermudatriangles.
- Poster: png