AI Paper Atlas

Research map / Graph learning / GNN architectures

EIGNN: Efficient Infinite-Depth Graph Neural Networks

Juncheng Liu, Kenji Kawaguchi, Bryan Hooi, Yiwei Wang, Xiaokui Xiao

NeurIPS 2021 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 8 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 EIGNN instead of H2GCNNode classification · Cornellaccuracy (%): 82.22 -> 85.13Improved
Use EIGNN instead of H2GCNNode classification · Texasaccuracy (%): 84.76 -> 84.60Hurt
Use EIGNN instead of H2GCNNode classification · Wisconsinaccuracy (%): 85.88 -> 86.86Improved
Use EIGNN instead of H2GCNNode classification · Chameleonaccuracy (%): 60.30 -> 62.92Improved
Use EIGNN instead of H2GCNNode classification · Squirrelaccuracy (%): 40.75 -> 46.37Improved
Use EIGNN instead of IGNNMulti-label node classification · PPIMicro-F1 (%): 97.6 -> 98.0Improved
Replace IGNN's iterative solver with EIGNN's closed-form, eigendecomposition-based computationInfinite-depth GNN training · Chains (l=100, n_c=20)training time per epoch: 27.36ms -> 4.05msImproved
Replace IGNN's iterative solver with EIGNN's closed-form, eigendecomposition-based computationInfinite-depth GNN training · Chains (l=200, n_c=20)training time per epoch: 29.88ms -> 8.03msImproved
Replace IGNN's iterative solver with EIGNN's closed-form, eigendecomposition-based computationInfinite-depth GNN training · Chains (l=100, n_c=30)training time per epoch: 64.94ms -> 6.03msImproved
Replace IGNN's iterative solver with EIGNN's closed-form, eigendecomposition-based computationInfinite-depth GNN training · Chains (l=200, n_c=30)training time per epoch: 60.31ms -> 16.0msImproved
Use EIGNN instead of IGNN under feature perturbationNode classification · Cornell (FGSM 0.01)accuracy (%): 57.30 -> 72.70Improved
Use EIGNN instead of IGNN under feature perturbationNode classification · Texas (FGSM 0.01)accuracy (%): 53.51 -> 74.59Improved

Later papers that compared with this method

4 later accepted papers report EIGNN as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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