atlas

Research map / Learning theory and algorithms / Clustering

Nearly-Optimal Hierarchical Clustering for Well-Clustered Graphs

ICML 2023 · Learning theory and algorithms › Clustering · approach: Correlation clustering · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace arbitrary-vertex bucketing with SpecWRSC (spectral clustering + degree bucketing + WRSC) versus MS, Linkage++, AverageLinkageHierarchical clustering on real-world datasets · Iris, Wine, Cancer, Newsgrouprunning time: lowest of four methods on all datasetsHelped
SpecWRSC algorithm versus MS and Linkage++ baselinesDasgupta cost on real-world datasets · Iris, Wine, Cancer, NewsgroupDasgupta cost: lower cost than MS and Linkage++ (figure only)Helped
SpecWRSC on GEMSEC Facebook artist graphScalability · GEMSEC Facebook artist (50,515 nodes)running time: only method finishing within 12 hoursHelped
SpecWRSC on synthetic SBM with 100,000 nodesScalability · SBM n=100,000running time: finishes in ~4 hours while all others time out after 12 hoursHelped
Spectral-gap condition: SpecWRSC benefits when lambda_{k+1}/lambda_k is largeSpecWRSC on real-world datasets · Iris, Wine, Cancer, NewsgroupDasgupta cost relative to gapMixed

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