Robust Hypergraph Clustering via Convex Relaxation of Truncated MLE

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 958
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorLee, Jeonghwanko
dc.contributor.authorKim, Daesungko
dc.contributor.authorChung, Hye Wonko
dc.date.accessioned2021-01-14T08:50:06Z-
dc.date.available2021-01-14T08:50:06Z-
dc.date.created2020-11-25-
dc.date.issued2020-11-
dc.identifier.citationIEEE Journal on Selected Areas in Information Theory, v.1, no.3, pp.613 - 631-
dc.identifier.issn2641-8770-
dc.identifier.urihttp://hdl.handle.net/10203/279929-
dc.description.abstractWe study hypergraph clustering in the weighted d -uniform hypergraph stochastic block model ( d -WHSBM ), where each edge consisting of d nodes from the same community has higher expected weight than the edges consisting of nodes from different communities. We propose a new hypergraph clustering algorithm, called CRTMLE , and provide its performance guarantee under the d -WHSBM for general parameter regimes. We show that the proposed method achieves the order-wise optimal or the best existing results for approximately balanced community sizes. Moreover, our results settle the first recovery guarantees for growing number of clusters of unbalanced sizes. Involving theoretical analysis and empirical results, we demonstrate the robustness of our algorithm against the unbalancedness of community sizes or the presence of outlier nodes.-
dc.languageEnglish-
dc.publisherIEEE-
dc.titleRobust Hypergraph Clustering via Convex Relaxation of Truncated MLE-
dc.typeArticle-
dc.type.rimsART-
dc.citation.volume1-
dc.citation.issue3-
dc.citation.beginningpage613-
dc.citation.endingpage631-
dc.citation.publicationnameIEEE Journal on Selected Areas in Information Theory-
dc.identifier.doi10.1109/JSAIT.2020.3037170-
dc.contributor.localauthorChung, Hye Won-
dc.description.isOpenAccessN-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0