AI Paper Atlas

Research map / Graph learning / GNN architectures

Equivariant Hypergraph Neural Networks

Jinwoo Kim, Saeyoon Oh, Sungjun Cho, Seunghoon Hong

ECCV 2022 · 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 global interaction and order embedding (vs removing both) (ablation)EHNN-MLP · k-edge identification (seen k, ablation)accuracy (%): 78.94 -> 98.02Improved
add order embedding (vs removing it) (ablation)EHNN-MLP · k-edge identification (seen k, ablation)accuracy (%): 84.05 -> 98.02Improved
add global interaction (vs removing it) (ablation)EHNN-MLP · k-edge identification (seen k, ablation)accuracy (%): 80.34 -> 98.02Improved
use MLP realization instead of naive lookup table (ablation)EHNN · k-edge identification (seen k, ablation)accuracy (%): 87.09 -> 98.02Improved
use MLP realization instead of naive hypernetwork (ablation)EHNN · k-edge identification (seen k, ablation)accuracy (%): 83.74 -> 98.02Improved
replace message passing AllDeepSets with EHNN-MLP (ablation)AllDeepSets · k-edge identification (seen k)accuracy (%): 76.99 -> 98.02Improved
replace AllDeepSets with EHNN-MLP on unseen orders (extrapolation)AllDeepSets · k-edge identification (unseen k, extrapolation)accuracy (%): 79.01 -> 85.65Improved
add attention (EHNN-Transformer vs EHNN-MLP) on seen k (ablation)EHNN-MLP · k-edge identification (seen k)accuracy (%): 98.02 -> 99.69Improved
add attention (EHNN-Transformer vs EHNN-MLP) on extrapolation (ablation)EHNN-MLP · k-edge identification (unseen k, extrapolation)accuracy (%): 85.65 -> 90.19Improved
add attention (EHNN-Transformer vs EHNN-MLP) on Walmart(1)EHNN-MLP · Walmart(1) semi-supervisedaccuracy (%): 65.65 -> 68.73Improved
add attention (EHNN-Transformer vs EHNN-MLP) on WillowEHNN-MLP · Willow keypoint matching (avg)accuracy (%): 96.33 -> 97.08Improved
add attention (EHNN-Transformer vs EHNN-MLP) on PASCAL-VOCEHNN-MLP · PASCAL-VOC keypoint matching (avg)accuracy (%): 79.90 -> 79.74No clear effect

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