AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle

Xu Bai, Bin Lu, Kun Zhang, Shengbo Chen, Xinbing Wang, Chenghu Zhou, Meng Jin

ICML 2026 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 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
use NOPE* local-isotropy approximation instead of exact NOPENOPE · Citeseer coarsening r=0.5runtime: 0.97s -> 0.35sImproved
use NOPE* instead of NOPE (ablation)NOPE · Ogb-Arxiv coarsening r=0.5runtime: 5min12.79s -> 1min4.38sImproved
use NOPE* instead of NOPE (ablation)NOPE · Book coarsening r=0.5runtime: 44min48.80s -> 4min29.46sImproved
use NOPE* instead of NOPE at high coarsening ratio (ablation)NOPE · coarsening ratio r=0.7 case studylabel predictionHurt
use NOPE* approximation (ablation)NOPE · Citeseer LLM node classification r=0.5accuracy: 0.6206 -> 0.6018Hurt
use NOPE* approximation (ablation)NOPE · Book LLM node classification r=0.5accuracy: 0.9170 -> 0.9244Improved
add interference-aware (non-selfish) merging instead of selfish pairwise merginggreedy graph coarsening · Dirichlet Energy during coarseningDirichlet EnergyImproved
use NOPE instead of heuristic sampling (Random/Degree/RAG)LLM node classification · Products (subset) r=0.5accuracy: 0.5789 -> 0.6783Improved
use NOPE over UGCLLM node classification · Ogb-Arxiv r=0.5accuracy: 0.3482 -> 0.3808Improved
use NOPE instead of A-CMLLM node classification · Ogb-Arxiv r=0.5accuracy: 0.3925 -> 0.3808Hurt
raise coarsening rate for NOPENOPE · runtime at high rruntimeHurt
coarsen with NOPE and train GNN on coarsened graphGCN/GIN/SAGE · node classification r=0.5accuracyNo 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