AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Constant Curvature Graph Convolutional Networks

Gregor Bachmann, Gary Becigneul, Octavian Ganea

ICML 2020 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 36 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use hyperbolic κ-GCN for tree embeddings instead of the strongest Euclidean baselineGraph metric embedding · Treeaverage distortion: 0.045 -> 0.0029Improved
Use product spherical κ-GCN for toroidal embeddings instead of the strongest Euclidean baselineGraph metric embedding · Toroidalaverage distortion: 0.0603 -> 0.0464Improved
Use spherical κ-GCN for spherical graph embeddings instead of the strongest Euclidean baselineGraph metric embedding · Spherical Graphaverage distortion: 0.0409 -> 0.0337Improved
Use hyperbolic κ-GCN instead of Euclidean GCNNode classification · Citeseeraccuracy: 0.729 ± 0.0054 -> 0.732 ± 0.0051Improved
Use spherical κ-GCN instead of Euclidean GCNNode classification · Coraaccuracy: 0.814 ± 0.004 -> 0.819 ± 0.0045Improved
Use spherical κ-GCN instead of the strongest hyperbolic baselineNode classification · Pubmedaccuracy: 0.798 ± 0.0043 -> 0.788 ± 0.0049Hurt
Use hyperbolic κ-GCN instead of the strongest hyperbolic baselineNode classification · Airportaccuracy: 0.844 ± 0.0041 -> 0.819 ± 0.0033Hurt
Match the embedding geometry to the graph's underlying geometryκ-GCN graph embeddings · Tree, Toroidal, and Spherical Graphaverage distortionImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy