AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques

Debarghya Ghoshdastidar, Ambedkar Dukkipati

JMLR 2017 · Learning theory and algorithms › Clustering · approach: Correlation clustering · 41 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 TTM instead of HOSVDspectral hypergraph partitioning · Planted m-uniform hypergraph, k=2, p=0.1, n from 10 to 100mean number of mis-clustered verticesImproved
use TTM instead of NH-Cutspectral hypergraph partitioning · Planted m-uniform hypergraph, k=2, p=0.1, n from 10 to 100mean number of mis-clustered verticesNo clear effect
reduce probability gap p from 0.1 to 0.05 and 0.025HOSVD · Planted 3-uniform hypergraph bi-partitioning (q=0.2, 50 runs)mis-clustered vertices: error varies as 1/p^4Hurt
reduce probability gap p from 0.1 to 0.05 and 0.025TTM · Planted 3-uniform hypergraph bi-partitioning (q=0.2, 50 runs)mis-clustered vertices: error varies as 1/p^2Hurt
use TTM instead of SNTF and hMETIShypergraph partitioning · Planted 3-uniform hypergraph, k=3, q=0.2, 50 runsfractional clustering errorImproved
use TTM instead of HGThypergraph partitioning · Planted 3-uniform hypergraph, k=3, q=0.2, 50 runsfractional clustering errorImproved
increase noise level sigma_a in line clusteringall hypergraph partitioning methods · Noisy points from three intersecting lines in 3-Dfractional clustering errorHurt

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