AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective

Wenlong Lyu, Yuheng Jia, Hui Liu, Junhui Hou

JMLR 2026 · Learning theory and algorithms › Clustering · approach: Correlation 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
add block diagonal regularization (B-LoRD over LoRD) (ablation)LoRD · Average ACC over 9 datasetsACC: 0.636 -> 0.720Improved
use B-LoRD instead of second-best SDSSDS · Average ACC over 9 datasetsACC: 0.667 -> 0.720Improved
use adaptive tau-hat-1 instead of tuned tau (ablation)B-LoRD · Average ACC over 12 datasetsACC: 0.720 -> 0.670Hurt
use adaptive tau-hat-2 instead of tuned tau (ablation)B-LoRD · Average ACC over 12 datasetsACC: 0.720 -> 0.675Hurt
use true class prior mu* instead of uniform mu0 (ablation)LoRD · EcoliACC: 0.455 -> 0.717Improved
use true class prior mu* instead of uniform mu0 (ablation)B-LoRD · EcoliACC: 0.741 -> 0.801Improved
use true class prior mu* instead of uniform mu0 (ablation)LoRD · YeastACC: 0.303 -> 0.385Improved
use true class prior mu* instead of uniform mu0 (ablation)LoRD · WineACC: 0.944 -> 0.916Hurt
use true class prior mu* instead of uniform mu0 (ablation)B-LoRD · MNIST-2000ACC: 0.745 -> 0.742No clear effect
use true class prior mu* instead of uniform mu0 (ablation)LoRD · Synthetic Gaussians IBR 0.1761ACC: 0.620 -> 0.885Improved
add block diagonal regularization (B-LoRD over LoRD), uniform prior (ablation)LoRD · Synthetic Gaussians IBR 0.1761 (mu0)ACC: 0.620 -> 0.700Improved
replace Dykstra-based initialization with Sinkhorn-Knopp (ablation)LoRD and B-LoRD · initialization of Vclustering qualityImproved

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