On Phase Transitions in Learning Sparse Networks View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2007

AUTHORS

Goele Hollanders , Geert Jan Bex , Marc Gyssens , Ronald L. Westra , Karl Tuyls

ABSTRACT

In this paper we study the identification of sparse interaction networks as a machine learning problem. Sparsity mean that we are provided with a small data set and a high number of unknown components of the system, most of which are zero. Under these circumstances, a model needs to be learned that fits the underlying system, capable of generalization. This corresponds to the student-teacher setting in machine learning. In the first part of this paper we introduce a learning algorithm, based on L1-minimization, to identify interaction networks from poor data and analyze its dynamics with respect to phase transitions. The efficiency of the algorithm is measured by the generalization error, which represents the probability that the student is a good fit to the teacher. In the second part of this paper we show that from a system with a specific system size value the generalization error of other system sizes can be estimated. A comparison with a set of simulation experiments show a very good fit. More... »

PAGES

591-599

References to SciGraph publications

Book

TITLE

Machine Learning: ECML 2007

ISBN

978-3-540-74957-8
978-3-540-74958-5

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-74958-5_57

DOI

http://dx.doi.org/10.1007/978-3-540-74958-5_57

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1039533200


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "name": [
            "Department of Mathematics, Physics, and Computer Science, Hasselt University and Transnational University of Limburg, Hasselt, Belgium"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hollanders", 
        "givenName": "Goele", 
        "id": "sg:person.014110747731.80", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014110747731.80"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Department of Mathematics, Physics, and Computer Science, Hasselt University and Transnational University of Limburg, Hasselt, Belgium"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bex", 
        "givenName": "Geert Jan", 
        "id": "sg:person.07777231461.76", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07777231461.76"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Department of Mathematics, Physics, and Computer Science, Hasselt University and Transnational University of Limburg, Hasselt, Belgium"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gyssens", 
        "givenName": "Marc", 
        "id": "sg:person.07576220131.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07576220131.20"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Transnational University Limburg", 
          "id": "https://www.grid.ac/institutes/grid.440516.2", 
          "name": [
            "Department of Mathematics and Computer Science, Maastricht University and Transnational University of Limburg, Maastricht, The Netherlands"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Westra", 
        "givenName": "Ronald L.", 
        "id": "sg:person.012516006731.95", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012516006731.95"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Transnational University Limburg", 
          "id": "https://www.grid.ac/institutes/grid.440516.2", 
          "name": [
            "Department of Mathematics and Computer Science, Maastricht University and Transnational University of Limburg, Maastricht, The Netherlands"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tuyls", 
        "givenName": "Karl", 
        "id": "sg:person.012404541721.90", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012404541721.90"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1073/pnas.94.17.9147", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025449861"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1073/pnas.092576199", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028442768"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-71037-0_11", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030674614", 
          "https://doi.org/10.1007/978-3-540-71037-0_11"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1016/j.bulm.2003.08.010", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041437663", 
          "https://doi.org/10.1016/j.bulm.2003.08.010"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0022-5193(73)90208-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044522507"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1089/10665270252833208", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059204918"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tit.2004.828141", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061650125"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2007", 
    "datePublishedReg": "2007-01-01", 
    "description": "In this paper we study the identification of sparse interaction networks as a machine learning problem. Sparsity mean that we are provided with a small data set and a high number of unknown components of the system, most of which are zero. Under these circumstances, a model needs to be learned that fits the underlying system, capable of generalization. This corresponds to the student-teacher setting in machine learning. In the first part of this paper we introduce a learning algorithm, based on L1-minimization, to identify interaction networks from poor data and analyze its dynamics with respect to phase transitions. The efficiency of the algorithm is measured by the generalization error, which represents the probability that the student is a good fit to the teacher. In the second part of this paper we show that from a system with a specific system size value the generalization error of other system sizes can be estimated. A comparison with a set of simulation experiments show a very good fit.", 
    "editor": [
      {
        "familyName": "Kok", 
        "givenName": "Joost N.", 
        "type": "Person"
      }, 
      {
        "familyName": "Koronacki", 
        "givenName": "Jacek", 
        "type": "Person"
      }, 
      {
        "familyName": "Mantaras", 
        "givenName": "Raomon Lopez de", 
        "type": "Person"
      }, 
      {
        "familyName": "Matwin", 
        "givenName": "Stan", 
        "type": "Person"
      }, 
      {
        "familyName": "Mladeni\u010d", 
        "givenName": "Dunja", 
        "type": "Person"
      }, 
      {
        "familyName": "Skowron", 
        "givenName": "Andrzej", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-74958-5_57", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-74957-8", 
        "978-3-540-74958-5"
      ], 
      "name": "Machine Learning: ECML 2007", 
      "type": "Book"
    }, 
    "name": "On Phase Transitions in Learning Sparse Networks", 
    "pagination": "591-599", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-74958-5_57"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "bc514b8ed55da8ea1651e3457c782169762558742ebcddb6b1b8efc55d26bdef"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1039533200"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-74958-5_57", 
      "https://app.dimensions.ai/details/publication/pub.1039533200"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T05:33", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000346_0000000346/records_99818_00000002.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-540-74958-5_57"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74958-5_57'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74958-5_57'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74958-5_57'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74958-5_57'


 

This table displays all metadata directly associated to this object as RDF triples.

147 TRIPLES      23 PREDICATES      34 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-74958-5_57 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ne74996dc2f24418cb4bcdce2b40924c9
4 schema:citation sg:pub.10.1007/978-3-540-71037-0_11
5 sg:pub.10.1016/j.bulm.2003.08.010
6 https://doi.org/10.1016/0022-5193(73)90208-7
7 https://doi.org/10.1073/pnas.092576199
8 https://doi.org/10.1073/pnas.94.17.9147
9 https://doi.org/10.1089/10665270252833208
10 https://doi.org/10.1109/tit.2004.828141
11 schema:datePublished 2007
12 schema:datePublishedReg 2007-01-01
13 schema:description In this paper we study the identification of sparse interaction networks as a machine learning problem. Sparsity mean that we are provided with a small data set and a high number of unknown components of the system, most of which are zero. Under these circumstances, a model needs to be learned that fits the underlying system, capable of generalization. This corresponds to the student-teacher setting in machine learning. In the first part of this paper we introduce a learning algorithm, based on L1-minimization, to identify interaction networks from poor data and analyze its dynamics with respect to phase transitions. The efficiency of the algorithm is measured by the generalization error, which represents the probability that the student is a good fit to the teacher. In the second part of this paper we show that from a system with a specific system size value the generalization error of other system sizes can be estimated. A comparison with a set of simulation experiments show a very good fit.
14 schema:editor N8ff7c27cf9614880a72c55fb970887ab
15 schema:genre chapter
16 schema:inLanguage en
17 schema:isAccessibleForFree true
18 schema:isPartOf Ne4bf90e807574ec4b4cfa7b4a61f9316
19 schema:name On Phase Transitions in Learning Sparse Networks
20 schema:pagination 591-599
21 schema:productId N2a0bef546e564d4f860a1ee1f912089e
22 N681c0513f30e4a9eb7b37d404acd1359
23 N8b13067f9732498da63d0824d0dd0965
24 schema:publisher N7146c9202c694726975a4ca9a6181805
25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039533200
26 https://doi.org/10.1007/978-3-540-74958-5_57
27 schema:sdDatePublished 2019-04-16T05:33
28 schema:sdLicense https://scigraph.springernature.com/explorer/license/
29 schema:sdPublisher N217e7da4c2564965b5cab9cabcd1249a
30 schema:url https://link.springer.com/10.1007%2F978-3-540-74958-5_57
31 sgo:license sg:explorer/license/
32 sgo:sdDataset chapters
33 rdf:type schema:Chapter
34 N1806a72634d64acb9e5f59adf2bb40d2 rdf:first sg:person.07777231461.76
35 rdf:rest N406cf5e4c0704e168d51aed45b29d705
36 N18fc9952e1914d908f0596696b6166f9 schema:name Department of Mathematics, Physics, and Computer Science, Hasselt University and Transnational University of Limburg, Hasselt, Belgium
37 rdf:type schema:Organization
38 N1e4966c083e34533959c8035cf438732 schema:name Department of Mathematics, Physics, and Computer Science, Hasselt University and Transnational University of Limburg, Hasselt, Belgium
39 rdf:type schema:Organization
40 N217e7da4c2564965b5cab9cabcd1249a schema:name Springer Nature - SN SciGraph project
41 rdf:type schema:Organization
42 N295557181ad440988e13cb20ff616944 rdf:first N6ba03ea7125c4ca588bf9b4b781dc0d6
43 rdf:rest N99d65d5eef5a4df0adc736fc679ca853
44 N2a0bef546e564d4f860a1ee1f912089e schema:name readcube_id
45 schema:value bc514b8ed55da8ea1651e3457c782169762558742ebcddb6b1b8efc55d26bdef
46 rdf:type schema:PropertyValue
47 N3549af5c4e5b4ce49f4c1efa182a84c7 rdf:first sg:person.012516006731.95
48 rdf:rest N9580f990b9644d7aad27957d8c5b5253
49 N38ca808f67054f9db9782ce4bc6fac8c schema:familyName Skowron
50 schema:givenName Andrzej
51 rdf:type schema:Person
52 N406cf5e4c0704e168d51aed45b29d705 rdf:first sg:person.07576220131.20
53 rdf:rest N3549af5c4e5b4ce49f4c1efa182a84c7
54 N5c538e3a55c9430ebde85fd56a464c22 schema:familyName Mantaras
55 schema:givenName Raomon Lopez de
56 rdf:type schema:Person
57 N657e2b07ca324b88afff01f10349c3db schema:familyName Matwin
58 schema:givenName Stan
59 rdf:type schema:Person
60 N681c0513f30e4a9eb7b37d404acd1359 schema:name dimensions_id
61 schema:value pub.1039533200
62 rdf:type schema:PropertyValue
63 N6ba03ea7125c4ca588bf9b4b781dc0d6 schema:familyName Koronacki
64 schema:givenName Jacek
65 rdf:type schema:Person
66 N7146c9202c694726975a4ca9a6181805 schema:location Berlin, Heidelberg
67 schema:name Springer Berlin Heidelberg
68 rdf:type schema:Organisation
69 N82507009b403496dad4ae399634db6e4 rdf:first N38ca808f67054f9db9782ce4bc6fac8c
70 rdf:rest rdf:nil
71 N82aae1983fa4462781db479297b2b28c rdf:first N657e2b07ca324b88afff01f10349c3db
72 rdf:rest Na7783f51198d4d98a2cb50c71c18845c
73 N8b13067f9732498da63d0824d0dd0965 schema:name doi
74 schema:value 10.1007/978-3-540-74958-5_57
75 rdf:type schema:PropertyValue
76 N8ff7c27cf9614880a72c55fb970887ab rdf:first Nda0be448f66a4959887d24c611d4e3d1
77 rdf:rest N295557181ad440988e13cb20ff616944
78 N9580f990b9644d7aad27957d8c5b5253 rdf:first sg:person.012404541721.90
79 rdf:rest rdf:nil
80 N97a03a7f382a4248a896ff34aae338e2 schema:familyName Mladenič
81 schema:givenName Dunja
82 rdf:type schema:Person
83 N99d65d5eef5a4df0adc736fc679ca853 rdf:first N5c538e3a55c9430ebde85fd56a464c22
84 rdf:rest N82aae1983fa4462781db479297b2b28c
85 Na30275c1a9114ee9908ac0a1665a2515 schema:name Department of Mathematics, Physics, and Computer Science, Hasselt University and Transnational University of Limburg, Hasselt, Belgium
86 rdf:type schema:Organization
87 Na7783f51198d4d98a2cb50c71c18845c rdf:first N97a03a7f382a4248a896ff34aae338e2
88 rdf:rest N82507009b403496dad4ae399634db6e4
89 Nda0be448f66a4959887d24c611d4e3d1 schema:familyName Kok
90 schema:givenName Joost N.
91 rdf:type schema:Person
92 Ne4bf90e807574ec4b4cfa7b4a61f9316 schema:isbn 978-3-540-74957-8
93 978-3-540-74958-5
94 schema:name Machine Learning: ECML 2007
95 rdf:type schema:Book
96 Ne74996dc2f24418cb4bcdce2b40924c9 rdf:first sg:person.014110747731.80
97 rdf:rest N1806a72634d64acb9e5f59adf2bb40d2
98 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
99 schema:name Information and Computing Sciences
100 rdf:type schema:DefinedTerm
101 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
102 schema:name Artificial Intelligence and Image Processing
103 rdf:type schema:DefinedTerm
104 sg:person.012404541721.90 schema:affiliation https://www.grid.ac/institutes/grid.440516.2
105 schema:familyName Tuyls
106 schema:givenName Karl
107 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012404541721.90
108 rdf:type schema:Person
109 sg:person.012516006731.95 schema:affiliation https://www.grid.ac/institutes/grid.440516.2
110 schema:familyName Westra
111 schema:givenName Ronald L.
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012516006731.95
113 rdf:type schema:Person
114 sg:person.014110747731.80 schema:affiliation N1e4966c083e34533959c8035cf438732
115 schema:familyName Hollanders
116 schema:givenName Goele
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014110747731.80
118 rdf:type schema:Person
119 sg:person.07576220131.20 schema:affiliation Na30275c1a9114ee9908ac0a1665a2515
120 schema:familyName Gyssens
121 schema:givenName Marc
122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07576220131.20
123 rdf:type schema:Person
124 sg:person.07777231461.76 schema:affiliation N18fc9952e1914d908f0596696b6166f9
125 schema:familyName Bex
126 schema:givenName Geert Jan
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07777231461.76
128 rdf:type schema:Person
129 sg:pub.10.1007/978-3-540-71037-0_11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030674614
130 https://doi.org/10.1007/978-3-540-71037-0_11
131 rdf:type schema:CreativeWork
132 sg:pub.10.1016/j.bulm.2003.08.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041437663
133 https://doi.org/10.1016/j.bulm.2003.08.010
134 rdf:type schema:CreativeWork
135 https://doi.org/10.1016/0022-5193(73)90208-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044522507
136 rdf:type schema:CreativeWork
137 https://doi.org/10.1073/pnas.092576199 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028442768
138 rdf:type schema:CreativeWork
139 https://doi.org/10.1073/pnas.94.17.9147 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025449861
140 rdf:type schema:CreativeWork
141 https://doi.org/10.1089/10665270252833208 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059204918
142 rdf:type schema:CreativeWork
143 https://doi.org/10.1109/tit.2004.828141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061650125
144 rdf:type schema:CreativeWork
145 https://www.grid.ac/institutes/grid.440516.2 schema:alternateName Transnational University Limburg
146 schema:name Department of Mathematics and Computer Science, Maastricht University and Transnational University of Limburg, Maastricht, The Netherlands
147 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...