AI Paper Atlas

Research map / Graph learning / GNN architectures

From Hypergraph Energy Functions to Hypergraph Neural Networks

Yuxin Wang, Quan Gan, Xipeng Qiu, Xuanjing Huang, David Wipf

ICML 2023 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 0 citations (OpenAlex)

Read the paper

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 both clique and star expansion terms together (vs clique-only or star-only) (ablation)PhenomNN_simple · Cora (co-authorship), Pubmed (co-citation)accuracy: Cora: 77.62 full vs 77.06 clique-only / 77.28 star-only; Pubmed: 76.20 star-only ties full, clique-only 75.71Mixed
use both clique and star expansion terms together (vs clique-only or star-only) (ablation)PhenomNN · Cora (co-authorship), Pubmed (co-citation), Citeseeraccuracy: Cora 77.11 vs 76.74 clique-only / 76.83 star-only; Pubmed 78.12 vs 77.94 / 77.52Improved
add ReLU-based proximal energy with simplified energy (psi={W,I,I}) instead of full parameterized energyPhenomNN_simple vs PhenomNN · Cora (co-authorship) and co-citation datasetsaccuracy: PhenomNN_simple higher on Cora (77.62 vs 77.11) and Cora-cocitation tie; PhenomNN higher on DBLP, Pubmed, Citeseer, NTU2Mixed
hidden dimension reduced from 512 to 64 in PhenomNN_simple (ablation)PhenomNN_simple · House(1) and House(0.6)accuracy: House(1) 71.77 at 512 vs 68.66 at 64; House(0.6) 86.96 vs 85.44Hurt
hidden dimension reduced from 512 to 64 in PhenomNN_simple (ablation)PhenomNN_simple · ModelNet40*accuracy: 98.66 at 512 vs 98.51 at 64No clear effect
PhenomNN (energy-unfolded hypergraph layers) vs strongest baseline on co-citation/co-authorship benchmarksPhenomNN · Pubmed (co-citation), Citeseer, DBLPaccuracy: Pubmed 78.12 vs 75.8 (H-GCNII); Citeseer 65.77 vs 64.5Improved
PhenomNN_simple vs AllSetTransformer on visual/ModelNet40* and NTU2012* benchmarksPhenomNN_simple · NTU2012*, ModelNet40*, House(1)accuracy: NTU2012* 91.03 vs 88.69; ModelNet40* 98.66 vs 98.20; House(1) 71.77 vs 69.33Improved
PhenomNN_simple vs AllSetTransformer on YelpPhenomNN_simple · Yelpaccuracy: 32.26 vs 36.89Hurt

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