AI Paper Atlas

Research map / Graph learning / GNN architectures

MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy

Honghua Dong, Jiawei Xu, Yu Yang, Rui Zhao, Shiwen Wu, Chun Yuan, Xiu Li, Chris J. Maddison, Lei Han

NeurIPS 2023 · Graph learning › GNN architectures · approach: Expressive equivariant message passing

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
add graph hierarchy (h=1 -> h=5) with S-EdgePool, n=5 (ablation)MeGraph · Graph Theory Benchmark (medium)avg MSE: 8.440 -> 0.675Improved
repeat information exchange over mega graph (n=1 -> n=5) at h=5 (ablation)MeGraph with EdgePool · Graph Theory Benchmark (medium)avg MSE: 5.368 -> 2.215Improved
increase layers of flat GNN without hierarchy (n=5 -> n=10) (ablation)MeGraph h=1 · Graph Theory Benchmark (medium)avg MSE: 8.440 -> 7.006Improved
switch EdgePool (tau_c=2) to S-EdgePool with eta_v=0.3, tau_c=4 (ablation)MeGraph · Graph Theory Benchmark (medium)avg MSE: 2.215 -> 0.675Improved
replace Graph-UNets with MeGraphMeGraph vs Graph-UNets · Graph Theory Benchmark (medium)avg MSE: 1.581 -> 0.675Improved
replace X-Conv cross update with X-Pool (unpool) (ablation)MeGraph · Graph Theory Benchmark (medium)avg MSE: 0.675 -> 1.203Hurt
remove bidirectional pathway (w/o pw) (ablation)MeGraph · Graph Theory Benchmark (medium)avg MSE: 0.675 -> 1.065Hurt
increase node pooling ratio eta_v from 0.3 to 0.5 (ablation)MeGraph S-EdgePool · Graph Theory Benchmark (medium)avg MSE: 0.675 -> 1.197Hurt
random pooling instead of EdgePool/Louvain (ablation)MeGraph · TreeCycle and TreeGridnode classification accuracyHurt
add MeGraph on large-size graphs vs h=1 baselineMeGraph · Graph Theory Benchmark (large)avg MSE: 220.169 -> 23.9676Improved
repeat local aggregation (n=1 -> MeGraph) on CLUSTER (ablation)MeGraph · CLUSTERaccuracy: 50.396 -> 68.603Improved
increase n from 1 to 4 at h=9 (ablation)MeGraph · LRGB Peptide-funcAP: 67.52 -> 69.45Improved

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