AI Paper Atlas

Research map / Graph learning / GNN architectures

Adaptive Neural Message Passing for Inductive Learning on Hypergraphs

Devanshu Arya, Deepak Kumar Gupta, Stevan Rudinac, Marcel Worring

TPAMI 2024 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 29 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
add adaptive node-importance (attention) weighting (ablation)HyperMSG · Coraaccuracy: 74.9 -> 77.7Improved
add adaptive node-importance weighting (ablation)HyperMSG · DBLPaccuracy: 80.4 -> 85.7Improved
add adaptive node-importance weighting (ablation)HyperMSG · Pubmedaccuracy: 76.2 -> 77.1Improved
add adaptive node-importance weighting (ablation)HyperMSG · Citeseeraccuracy: 66.4 -> 66.8Improved
add adaptive node-importance weighting (ablation)HyperMSG · Autism neuroimagingAUC-ROC: 64.3 -> 67.2Improved
add adaptive node-importance weighting (ablation)HyperMSG · MIR Flickr unseenaverage precision: 0.68 -> 0.69Improved
use hypergraph instead of graph representation (ablation)HyperMSG non-adaptive · Cora co-citationaccuracy: 64.2 -> 69.3Improved
use hypergraph instead of graph representation (ablation)HyperMSG non-adaptive · Pubmedaccuracy: 73.8 -> 76.2Improved
use hypergraph instead of graph representation (ablation)HyperMSG non-adaptive · Cora co-authorshipaccuracy: 73.9 -> 74.9Improved
increase neighbor samples alpha from 4 to 16 (ablation)HyperMSG · DBLP unseenaccuracy: 72.2 -> 81.5Improved
increase neighbor samples alpha from 8 to 16 (ablation)HyperMSG · Pubmed unseenaccuracy: 83.5 -> 81.7Hurt
use HyperMSG instead of UniGCNHyperMSG · DBLPaccuracy: 88.0 -> 85.7Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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