AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Clustering with Self-Learned Graph Regression

Lai Wei, Jin Liu

AAAI 2026 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering · 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 self-learned graph regularizer instead of k-nn graph regularizer (ablation)SGR · COIL100ACC (%): 65.28 -> 82.79Improved
use self-learned graph regularizer instead of k-nn graph regularizer (ablation)SGR · JAFFEACC (%): 98.12 -> 99.53Improved
use self-learned graph regularizer instead of k-nn graph regularizer (ablation)SGR · MNISTACC (%): 59.22 -> 68.21Improved
put hard-rank constraint on auxiliary C rather than on S (ablation)SGR · MNISTACC (%): 34.49 -> 68.21Improved
put hard-rank constraint on auxiliary C rather than on S (ablation)SGR · COIL20ACC (%): 87.36 -> 98.33Improved
cluster from S instead of C (ablation)SGR · JAFFEACC (%): 92.96 -> 99.53Improved
cluster from S instead of C (ablation)SGR · MNISTNMI (%): 69.04 (C) vs 75.82 (S)Hurt
SGR-S vs strongest baseline SDSGCSGR · COIL20ACC (%): 84.72 -> 98.33Improved
SGR-S vs strongest baseline SDSGCSGR · ZooACC (%): 67.33 -> 82.18Improved
restrict updates to k-nn sparsity pattern (acceleration, k=30 vs n-1) (ablation)SGR · runtimerunning timeImproved
vary alpha and beta in grid (ablation)SGR-S · six datasetsNMINo clear effect
vary neighborhood size k in {20,30,40,50,n-1} (ablation)SGR · six datasetsNMINo 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