AI Paper Atlas

Research map / Graph learning / GNN architectures

How Wide and How Deep? Mitigating Over-squashing of GNNs via Channel Capacity Constrained Estimation

Zinuo You, Jin Zheng, John Cartlidge

AAAI 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 0 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
choose hidden dimension and depth with C3E instead of heuristic defaultsGCN · Coraaccuracy: 0.808 -> 0.837Improved
choose hidden dimension and depth with C3EJacobiConv · Chameleonaccuracy: 0.423 -> 0.469Improved
choose hidden dimension and depth with C3EAPPNP · ogbn-papers100Maccuracy: 0.637 -> 0.681Improved
choose dimensions with C3EGPRGNN · Chameleonaccuracy: 0.348 -> 0.379Improved
increase propagation depth from 1 to 7 with fixed width 16 (ablation)GCN · Citeseeraccuracy: 0.707 -> 0.550Hurt
increase depth from 1 to 7 with C3E-estimated widths (ablation)GCN · Citeseeraccuracy: 0.716 -> 0.714 (L=2 to 7)No clear effect
increase hidden dimension (ablation)spectral GNNs · theory / Table 3representation compression ratioImproved

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