AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Local Hyper-Flow Diffusion

Kimon Fountoulakis, Pan Li, Shenghao Yang

NeurIPS 2021 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 2 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 submodular cut-cost instead of unit cut-cost (ablation)HFD · Florida Bay, LowF1: 0.47 -> 0.62Improved
use submodular cut-cost instead of unit cut-cost (ablation)HFD · Florida Bay, HighF1: 0.64 -> 0.84Improved
use submodular cut-cost instead of unit cut-cost (ablation)HFD · Florida Bay, Prod.F1: 0.69 -> 0.69No clear effect
use cardinality-based cut-cost instead of unit cut-cost (ablation)HFD · Florida Bay, Prod./Low/HighF1: 0.69 -> 0.67No clear effect
use cardinality-based cut-cost instead of unit cut-cost (ablation)HFD · Trivago-clicks PRIF1: 0.89 -> 0.95Improved
use cardinality-based cut-cost instead of unit cut-cost (ablation)HFD · Trivago-clicks UA-43F1: 0.85 -> 0.94Improved
use cardinality-based cut-cost instead of unit cut-cost (ablation)HFD · Trivago-clicks HKGF1: 0.82 -> 0.80Hurt
use cardinality-based cut-cost instead of unit cut-cost (ablation)LH-2.0 · Trivago-clicks HKGF1: 0.92 -> 0.94Improved
replace LH-2.0 diffusion with HFD (unit cut-cost)local clustering · Amazon-reviews cluster 12F1: 0.29 -> 0.92Improved
replace LH-1.4 diffusion with HFD (unit cut-cost)local clustering · Amazon-reviews cluster 18F1: 0.31 -> 0.80Improved
replace LH-1.4 diffusion with HFD (unit cut-cost)local clustering · Amazon-reviews cluster 15F1: 0.04 -> 0.00Hurt
replace ACL with HFD (unit cut-cost)local clustering · Amazon-reviews cluster 24F1: 0.20 -> 0.81Improved

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