@inproceedings{pham-chen-2018-large,
title = "Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs",
author = "Pham, Khiem and
Chen, Guangliang",
editor = "Glava{\v{s}}, Goran and
Somasundaran, Swapna and
Riedl, Martin and
Hovy, Eduard",
booktitle = "Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing ({T}ext{G}raphs-12)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-1705/",
doi = "10.18653/v1/W18-1705",
pages = "28--37",
abstract = "Spectral clustering has received a lot of attention due to its ability to separate nonconvex, non-intersecting manifolds, but its high computational complexity has significantly limited its applicability. Motivated by the document-term co-clustering framework by Dhillon (2001), we propose a landmark-based scalable spectral clustering approach in which we first use the selected landmark set and the given data to form a bipartite graph and then run a diffusion process on it to obtain a family of diffusion coordinates for clustering. We show that our proposed algorithm can be implemented based on very efficient operations on the affinity matrix between the given data and selected landmarks, thus capable of handling large data. Finally, we demonstrate the excellent performance of our method by comparing with the state-of-the-art scalable algorithms on several benchmark data sets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-chen-2018-large">
<titleInfo>
<title>Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khiem</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangliang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swapna</namePart>
<namePart type="family">Somasundaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Riedl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spectral clustering has received a lot of attention due to its ability to separate nonconvex, non-intersecting manifolds, but its high computational complexity has significantly limited its applicability. Motivated by the document-term co-clustering framework by Dhillon (2001), we propose a landmark-based scalable spectral clustering approach in which we first use the selected landmark set and the given data to form a bipartite graph and then run a diffusion process on it to obtain a family of diffusion coordinates for clustering. We show that our proposed algorithm can be implemented based on very efficient operations on the affinity matrix between the given data and selected landmarks, thus capable of handling large data. Finally, we demonstrate the excellent performance of our method by comparing with the state-of-the-art scalable algorithms on several benchmark data sets.</abstract>
<identifier type="citekey">pham-chen-2018-large</identifier>
<identifier type="doi">10.18653/v1/W18-1705</identifier>
<location>
<url>https://aclanthology.org/W18-1705/</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>28</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs
%A Pham, Khiem
%A Chen, Guangliang
%Y Glavaš, Goran
%Y Somasundaran, Swapna
%Y Riedl, Martin
%Y Hovy, Eduard
%S Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana, USA
%F pham-chen-2018-large
%X Spectral clustering has received a lot of attention due to its ability to separate nonconvex, non-intersecting manifolds, but its high computational complexity has significantly limited its applicability. Motivated by the document-term co-clustering framework by Dhillon (2001), we propose a landmark-based scalable spectral clustering approach in which we first use the selected landmark set and the given data to form a bipartite graph and then run a diffusion process on it to obtain a family of diffusion coordinates for clustering. We show that our proposed algorithm can be implemented based on very efficient operations on the affinity matrix between the given data and selected landmarks, thus capable of handling large data. Finally, we demonstrate the excellent performance of our method by comparing with the state-of-the-art scalable algorithms on several benchmark data sets.
%R 10.18653/v1/W18-1705
%U https://aclanthology.org/W18-1705/
%U https://doi.org/10.18653/v1/W18-1705
%P 28-37
Markdown (Informal)
[Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs](https://aclanthology.org/W18-1705/) (Pham & Chen, TextGraphs 2018)
ACL