AI Paper Atlas

Research map / Graph learning / GNN architectures

Simplified Graph Convolution with Heterophily

Sudhanshu Chanpuriya, Cameron N Musco

NeurIPS 2022 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 6 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
use ASGC (adaptive Krylov filter) instead of SGCSGC · Chameleonaccuracy: 57.70 -> 72.28Improved
use ASGC instead of SGCSGC · Squirrelaccuracy: 44.98 -> 58.98Improved
use ASGC instead of SGCSGC · Texasaccuracy: 55.68 -> 86.76Improved
use ASGC instead of SGCSGC · Cornellaccuracy: 54.32 -> 86.22Improved
use ASGC instead of SGCSGC · Actoraccuracy: 30.07 -> 36.45Improved
use ASGC instead of SGCSGC · PubMedaccuracy: 73.90 -> 79.05Improved
use ASGC instead of SGC on homophilous CoraSGC · Coraaccuracy: 78.16 -> 73.93Hurt
use ASGC instead of SGC on homophilous CiteseerSGC · Citeseeraccuracy: 70.18 -> 67.73Hurt
use ASGC instead of SGC on Computers and PhotoSGC · Computersaccuracy: 87.14 -> 86.72No clear effect
use ASGC instead of GPRGNN on TexasGPRGNN · Texasaccuracy: 92.92 -> 86.76Hurt
use ASGC instead of GPRGNN on ChameleonGPRGNN · Chameleonaccuracy: 67.48 -> 72.28Improved
use ASGC instead of GCN on ChameleonGCN · Chameleonaccuracy: 60.96 -> 72.28Improved

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