Hypergraph \(p\)-Laplacian: A Differential Geometry View

Guardat en:
Dades bibliogràfiques
Publicat a:arXiv.org (Nov 22, 2017), p. n/a
Autor principal: Saito, Shota
Altres autors: Mandic, Danilo P, Suzuki, Hideyuki
Publicat:
Cornell University Library, arXiv.org
Matèries:
Accés en línia:Citation/Abstract
Full text outside of ProQuest
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 2076673762
003 UK-CbPIL
022 |a 2331-8422 
024 7 |a 10.1609/aaai.v32i1.11823  |2 doi 
035 |a 2076673762 
045 0 |b d20171122 
100 1 |a Saito, Shota 
245 1 |a Hypergraph \(p\)-Laplacian: A Differential Geometry View 
260 |b Cornell University Library, arXiv.org  |c Nov 22, 2017 
513 |a Working Paper 
520 3 |a The graph Laplacian plays key roles in information processing of relational data, and has analogies with the Laplacian in differential geometry. In this paper, we generalize the analogy between graph Laplacian and differential geometry to the hypergraph setting, and propose a novel hypergraph \(p\)-Laplacian. Unlike the existing two-node graph Laplacians, this generalization makes it possible to analyze hypergraphs, where the edges are allowed to connect any number of nodes. Moreover, we propose a semi-supervised learning method based on the proposed hypergraph \(p\)-Laplacian, and formalize them as the analogue to the Dirichlet problem, which often appears in physics. We further explore theoretical connections to normalized hypergraph cut on a hypergraph, and propose normalized cut corresponding to hypergraph \(p\)-Laplacian. The proposed \(p\)-Laplacian is shown to outperform standard hypergraph Laplacians in the experiment on a hypergraph semi-supervised learning and normalized cut setting. 
653 |a Data processing 
653 |a Dirichlet problem 
653 |a Graphs 
653 |a Differential geometry 
653 |a Graph theory 
653 |a Geometry 
700 1 |a Mandic, Danilo P 
700 1 |a Suzuki, Hideyuki 
773 0 |t arXiv.org  |g (Nov 22, 2017), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/2076673762/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/1711.08171