Bermuda Triangles: GNNs Fail to Detect Simple Topological StructuresDownload PDF

Mar 08, 2021 (edited Apr 08, 2021)GTRL 2021 PosterReaders: Everyone
  • 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
1 Reply

Loading