Semi-Supervised Boosting for Multi-Class Classification View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2008-01-01

AUTHORS

Hamed Valizadegan , Rong Jin , Anil K. Jain

ABSTRACT

Most semi-supervised learning algorithms have been designed for binary classification, and are extended to multi-class classification by approaches such as one-against-the-rest. The main shortcoming of these approaches is that they are unable to exploit the fact that each example is only assigned to one class. Additional problems with extending semi-supervised binary classifiers to multi-class problems include imbalanced classification and different output scales of different binary classifiers. We propose a semi-supervised boosting framework, termed Multi-Class Semi-Supervised Boosting (MCSSB), that directly solves the semi-supervised multi-class learning problem. Compared to the existing semi-supervised boosting methods, the proposed framework is advantageous in that it exploits both classification confidence and similarities among examples when deciding the pseudo-labels for unlabeled examples. Empirical study with a number of UCI datasets shows that the proposed MCSSB algorithm performs better than the state-of-the-art boosting algorithms for semi-supervised learning. More... »

PAGES

522-537

Book

TITLE

Machine Learning and Knowledge Discovery in Databases

ISBN

978-3-540-87480-5
978-3-540-87481-2

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-87481-2_34

DOI

http://dx.doi.org/10.1007/978-3-540-87481-2_34

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1011686383


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Computer Science and Engineering, Michigan State University", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Department of Computer Science and Engineering, Michigan State University"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Valizadegan", 
        "givenName": "Hamed", 
        "id": "sg:person.01042235270.74", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01042235270.74"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science and Engineering, Michigan State University", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Department of Computer Science and Engineering, Michigan State University"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jin", 
        "givenName": "Rong", 
        "id": "sg:person.01274430471.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01274430471.12"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science and Engineering, Michigan State University", 
          "id": "http://www.grid.ac/institutes/grid.17088.36", 
          "name": [
            "Department of Computer Science and Engineering, Michigan State University"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jain", 
        "givenName": "Anil K.", 
        "id": "sg:person.01031110710.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2008-01-01", 
    "datePublishedReg": "2008-01-01", 
    "description": "Most semi-supervised learning algorithms have been designed for binary classification, and are extended to multi-class classification by approaches such as one-against-the-rest. The main shortcoming of these approaches is that they are unable to exploit the fact that each example is only assigned to one class. Additional problems with extending semi-supervised binary classifiers to multi-class problems include imbalanced classification and different output scales of different binary classifiers. We propose a semi-supervised boosting framework, termed Multi-Class Semi-Supervised Boosting (MCSSB), that directly solves the semi-supervised multi-class learning problem. Compared to the existing semi-supervised boosting methods, the proposed framework is advantageous in that it exploits both classification confidence and similarities among examples when deciding the pseudo-labels for unlabeled examples. Empirical study with a number of UCI datasets shows that the proposed MCSSB algorithm performs better than the state-of-the-art boosting algorithms for semi-supervised learning.", 
    "editor": [
      {
        "familyName": "Daelemans", 
        "givenName": "Walter", 
        "type": "Person"
      }, 
      {
        "familyName": "Goethals", 
        "givenName": "Bart", 
        "type": "Person"
      }, 
      {
        "familyName": "Morik", 
        "givenName": "Katharina", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-87481-2_34", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-87480-5", 
        "978-3-540-87481-2"
      ], 
      "name": "Machine Learning and Knowledge Discovery in Databases", 
      "type": "Book"
    }, 
    "keywords": [
      "multi-class classification", 
      "binary classifier", 
      "semi-supervised learning algorithm", 
      "multi-class learning problems", 
      "semi-supervised learning", 
      "multi-class problems", 
      "different binary classifiers", 
      "Semi-Supervised Boosting", 
      "learning algorithm", 
      "unlabeled examples", 
      "imbalanced classification", 
      "classification confidence", 
      "boosting framework", 
      "UCI datasets", 
      "binary classification", 
      "learning problem", 
      "algorithm", 
      "classifier", 
      "classification", 
      "boosting", 
      "main shortcomings", 
      "framework", 
      "empirical study", 
      "dataset", 
      "additional problems", 
      "learning", 
      "example", 
      "output scale", 
      "Semi", 
      "shortcomings", 
      "art", 
      "similarity", 
      "method", 
      "confidence", 
      "class", 
      "number", 
      "state", 
      "fact", 
      "scale", 
      "rest", 
      "study", 
      "problem", 
      "approach"
    ], 
    "name": "Semi-Supervised Boosting for Multi-Class Classification", 
    "pagination": "522-537", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1011686383"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-87481-2_34"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-87481-2_34", 
      "https://app.dimensions.ai/details/publication/pub.1011686383"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:55", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_70.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-540-87481-2_34"
  }
]
 

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.10.1007/978-3-540-87481-2_34'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-87481-2_34'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-87481-2_34'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-87481-2_34'


 

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

126 TRIPLES      22 PREDICATES      67 URIs      60 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-87481-2_34 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nf8ef22dd5fd8482a980111f437326db8
4 schema:datePublished 2008-01-01
5 schema:datePublishedReg 2008-01-01
6 schema:description Most semi-supervised learning algorithms have been designed for binary classification, and are extended to multi-class classification by approaches such as one-against-the-rest. The main shortcoming of these approaches is that they are unable to exploit the fact that each example is only assigned to one class. Additional problems with extending semi-supervised binary classifiers to multi-class problems include imbalanced classification and different output scales of different binary classifiers. We propose a semi-supervised boosting framework, termed Multi-Class Semi-Supervised Boosting (MCSSB), that directly solves the semi-supervised multi-class learning problem. Compared to the existing semi-supervised boosting methods, the proposed framework is advantageous in that it exploits both classification confidence and similarities among examples when deciding the pseudo-labels for unlabeled examples. Empirical study with a number of UCI datasets shows that the proposed MCSSB algorithm performs better than the state-of-the-art boosting algorithms for semi-supervised learning.
7 schema:editor Nd2f6a5dca15e4f658af491fd4ca23875
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N46b2c7fd0cc0430e9cc4fde77f8e3f90
11 schema:keywords Semi
12 Semi-Supervised Boosting
13 UCI datasets
14 additional problems
15 algorithm
16 approach
17 art
18 binary classification
19 binary classifier
20 boosting
21 boosting framework
22 class
23 classification
24 classification confidence
25 classifier
26 confidence
27 dataset
28 different binary classifiers
29 empirical study
30 example
31 fact
32 framework
33 imbalanced classification
34 learning
35 learning algorithm
36 learning problem
37 main shortcomings
38 method
39 multi-class classification
40 multi-class learning problems
41 multi-class problems
42 number
43 output scale
44 problem
45 rest
46 scale
47 semi-supervised learning
48 semi-supervised learning algorithm
49 shortcomings
50 similarity
51 state
52 study
53 unlabeled examples
54 schema:name Semi-Supervised Boosting for Multi-Class Classification
55 schema:pagination 522-537
56 schema:productId N4b9375a8e02747b4b7c84c60da197c38
57 Nd76633c3b0d346e0b09be4c1d8faed94
58 schema:publisher Ndc1b5de1ae7240a2a82cda736dc2fa82
59 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011686383
60 https://doi.org/10.1007/978-3-540-87481-2_34
61 schema:sdDatePublished 2022-12-01T06:55
62 schema:sdLicense https://scigraph.springernature.com/explorer/license/
63 schema:sdPublisher N141b7cff49914820bd34208efab18c53
64 schema:url https://doi.org/10.1007/978-3-540-87481-2_34
65 sgo:license sg:explorer/license/
66 sgo:sdDataset chapters
67 rdf:type schema:Chapter
68 N141b7cff49914820bd34208efab18c53 schema:name Springer Nature - SN SciGraph project
69 rdf:type schema:Organization
70 N1d112d1866cf4e7da18409303fda052d schema:familyName Morik
71 schema:givenName Katharina
72 rdf:type schema:Person
73 N306936564dc2403a8f99941b217ec95a schema:familyName Goethals
74 schema:givenName Bart
75 rdf:type schema:Person
76 N46b2c7fd0cc0430e9cc4fde77f8e3f90 schema:isbn 978-3-540-87480-5
77 978-3-540-87481-2
78 schema:name Machine Learning and Knowledge Discovery in Databases
79 rdf:type schema:Book
80 N4b9375a8e02747b4b7c84c60da197c38 schema:name doi
81 schema:value 10.1007/978-3-540-87481-2_34
82 rdf:type schema:PropertyValue
83 N56175406e6934f659a0cc258f575e493 rdf:first N306936564dc2403a8f99941b217ec95a
84 rdf:rest N76942afb32cb4537877162ac2a0028cd
85 N6bfe3437198c49129786ea2b9fe47ab2 schema:familyName Daelemans
86 schema:givenName Walter
87 rdf:type schema:Person
88 N76942afb32cb4537877162ac2a0028cd rdf:first N1d112d1866cf4e7da18409303fda052d
89 rdf:rest rdf:nil
90 Nb11354848571489b8589be0ccefafe63 rdf:first sg:person.01031110710.30
91 rdf:rest rdf:nil
92 Nd2f6a5dca15e4f658af491fd4ca23875 rdf:first N6bfe3437198c49129786ea2b9fe47ab2
93 rdf:rest N56175406e6934f659a0cc258f575e493
94 Nd76633c3b0d346e0b09be4c1d8faed94 schema:name dimensions_id
95 schema:value pub.1011686383
96 rdf:type schema:PropertyValue
97 Ndc1b5de1ae7240a2a82cda736dc2fa82 schema:name Springer Nature
98 rdf:type schema:Organisation
99 Nf8ef22dd5fd8482a980111f437326db8 rdf:first sg:person.01042235270.74
100 rdf:rest Nf9d2daadc305492e9c6d0c8a88fb3975
101 Nf9d2daadc305492e9c6d0c8a88fb3975 rdf:first sg:person.01274430471.12
102 rdf:rest Nb11354848571489b8589be0ccefafe63
103 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
104 schema:name Information and Computing Sciences
105 rdf:type schema:DefinedTerm
106 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
107 schema:name Artificial Intelligence and Image Processing
108 rdf:type schema:DefinedTerm
109 sg:person.01031110710.30 schema:affiliation grid-institutes:grid.17088.36
110 schema:familyName Jain
111 schema:givenName Anil K.
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031110710.30
113 rdf:type schema:Person
114 sg:person.01042235270.74 schema:affiliation grid-institutes:grid.17088.36
115 schema:familyName Valizadegan
116 schema:givenName Hamed
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01042235270.74
118 rdf:type schema:Person
119 sg:person.01274430471.12 schema:affiliation grid-institutes:grid.17088.36
120 schema:familyName Jin
121 schema:givenName Rong
122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01274430471.12
123 rdf:type schema:Person
124 grid-institutes:grid.17088.36 schema:alternateName Department of Computer Science and Engineering, Michigan State University
125 schema:name Department of Computer Science and Engineering, Michigan State University
126 rdf:type schema:Organization
 




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


...