AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets

Fuli Wang, Wei Qian, Daniel L. Lau, Gonzalo R. Arce

TPAMI 2026 · Graph learning › Graph self-supervised learning · approach: Graph domain adaptation · 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
add PHPool to HGAT backbone (ablation)HGAT · MUTAGaccuracy: 74.53 -> 86.73Improved
add PHPool to HGNN backbone (ablation)HGNN · IMDB-BINARYaccuracy: 72.78 -> 74.88Improved
add PHPool to HGXConv backbone (ablation)HGXConv · IMDB-MULTIaccuracy: 50.76 -> 55.31Improved
replace SEPool with PHPool on HGXConv (ablation)SEPool+HGXConv · COLLABaccuracy: 80.73 -> 83.26Improved
replace TopKPool with PHPool on HGXConv (ablation)TopKPool+HGXConv · COLLABaccuracy: 68.55 -> 83.26Improved
replace attention backbone HGAT with HGXConv under PHPool (ablation)PHPool+HGAT · MUTAGaccuracy: 86.73 -> 86.42Hurt
use HGXConv instead of HGNN under PHPool (ablation)PHPool+HGNN · D&Daccuracy: 77.93 -> 79.88Improved
use HGXConv instead of GCN-style convolution alone (no pooling)HGXConv · MUTAGaccuracy: 73.37 vs 74.53 (HGAT)Mixed
increase pooling depth beyond 3 (ablation)HGUN encoder · COLLABaccuracy: sharp degradation at depth 5Hurt
use TopK node-drop pooling at depth 4 (ablation)TopK · D&Daccuracy: dropping 11 pointsHurt
use HGUN instead of BWGNNBWGNN · Yelp anomaly detectionF1-macro: 0.7232 -> 0.7732Improved
use HGUN instead of HGXConv without U-Net (ablation)HGXConv · Yelp anomaly detectionF1-macro: 0.7227 -> 0.7732Improved

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