Compositional metric learning for multi-label classification
Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise cons...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Sun, Yan-Ping [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2020 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Higher Education Press 2020 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Frontiers of computer science in China - Beijing : Higher Education Press, 2007, 15(2020), 5 vom: 31. Dez. |
|---|---|
| Übergeordnetes Werk: |
volume:15 ; year:2020 ; number:5 ; day:31 ; month:12 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11704-020-9294-7 |
|---|
| Katalog-ID: |
SPR05114851X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR05114851X | ||
| 003 | DE-627 | ||
| 005 | 20230509120556.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230508s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11704-020-9294-7 |2 doi | |
| 035 | |a (DE-627)SPR05114851X | ||
| 035 | |a (SPR)s11704-020-9294-7-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Sun, Yan-Ping |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Compositional metric learning for multi-label classification |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © Higher Education Press 2020 | ||
| 520 | |a Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. | ||
| 650 | 4 | |a machine learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a multi-label learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a metric learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a compositional metric |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a positive semidefinite matrix decomposition |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Zhang, Min-Ling |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Frontiers of computer science in China |d Beijing : Higher Education Press, 2007 |g 15(2020), 5 vom: 31. Dez. |w (DE-627)545787726 |w (DE-600)2388878-7 |x 1673-7466 |7 nnns |
| 773 | 1 | 8 | |g volume:15 |g year:2020 |g number:5 |g day:31 |g month:12 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s11704-020-9294-7 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_23 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_31 | ||
| 912 | |a GBV_ILN_32 | ||
| 912 | |a GBV_ILN_39 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_60 | ||
| 912 | |a GBV_ILN_62 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_69 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_74 | ||
| 912 | |a GBV_ILN_90 | ||
| 912 | |a GBV_ILN_95 | ||
| 912 | |a GBV_ILN_100 | ||
| 912 | |a GBV_ILN_101 | ||
| 912 | |a GBV_ILN_105 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_120 | ||
| 912 | |a GBV_ILN_138 | ||
| 912 | |a GBV_ILN_152 | ||
| 912 | |a GBV_ILN_161 | ||
| 912 | |a GBV_ILN_171 | ||
| 912 | |a GBV_ILN_187 | ||
| 912 | |a GBV_ILN_224 | ||
| 912 | |a GBV_ILN_250 | ||
| 912 | |a GBV_ILN_281 | ||
| 912 | |a GBV_ILN_285 | ||
| 912 | |a GBV_ILN_293 | ||
| 912 | |a GBV_ILN_370 | ||
| 912 | |a GBV_ILN_602 | ||
| 912 | |a GBV_ILN_702 | ||
| 912 | |a GBV_ILN_2005 | ||
| 951 | |a AR | ||
| 952 | |d 15 |j 2020 |e 5 |b 31 |c 12 | ||
| author_variant |
y p s yps m l z mlz |
|---|---|
| matchkey_str |
article:16737466:2020----::opstoamtilannfrutlb |
| hierarchy_sort_str |
2020 |
| publishDate |
2020 |
| allfields |
10.1007/s11704-020-9294-7 doi (DE-627)SPR05114851X (SPR)s11704-020-9294-7-e DE-627 ger DE-627 rakwb eng Sun, Yan-Ping verfasserin aut Compositional metric learning for multi-label classification 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Higher Education Press 2020 Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. machine learning (dpeaa)DE-He213 multi-label learning (dpeaa)DE-He213 metric learning (dpeaa)DE-He213 compositional metric (dpeaa)DE-He213 positive semidefinite matrix decomposition (dpeaa)DE-He213 Zhang, Min-Ling aut Enthalten in Frontiers of computer science in China Beijing : Higher Education Press, 2007 15(2020), 5 vom: 31. Dez. (DE-627)545787726 (DE-600)2388878-7 1673-7466 nnns volume:15 year:2020 number:5 day:31 month:12 https://dx.doi.org/10.1007/s11704-020-9294-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2005 AR 15 2020 5 31 12 |
| spelling |
10.1007/s11704-020-9294-7 doi (DE-627)SPR05114851X (SPR)s11704-020-9294-7-e DE-627 ger DE-627 rakwb eng Sun, Yan-Ping verfasserin aut Compositional metric learning for multi-label classification 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Higher Education Press 2020 Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. machine learning (dpeaa)DE-He213 multi-label learning (dpeaa)DE-He213 metric learning (dpeaa)DE-He213 compositional metric (dpeaa)DE-He213 positive semidefinite matrix decomposition (dpeaa)DE-He213 Zhang, Min-Ling aut Enthalten in Frontiers of computer science in China Beijing : Higher Education Press, 2007 15(2020), 5 vom: 31. Dez. (DE-627)545787726 (DE-600)2388878-7 1673-7466 nnns volume:15 year:2020 number:5 day:31 month:12 https://dx.doi.org/10.1007/s11704-020-9294-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2005 AR 15 2020 5 31 12 |
| allfields_unstemmed |
10.1007/s11704-020-9294-7 doi (DE-627)SPR05114851X (SPR)s11704-020-9294-7-e DE-627 ger DE-627 rakwb eng Sun, Yan-Ping verfasserin aut Compositional metric learning for multi-label classification 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Higher Education Press 2020 Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. machine learning (dpeaa)DE-He213 multi-label learning (dpeaa)DE-He213 metric learning (dpeaa)DE-He213 compositional metric (dpeaa)DE-He213 positive semidefinite matrix decomposition (dpeaa)DE-He213 Zhang, Min-Ling aut Enthalten in Frontiers of computer science in China Beijing : Higher Education Press, 2007 15(2020), 5 vom: 31. Dez. (DE-627)545787726 (DE-600)2388878-7 1673-7466 nnns volume:15 year:2020 number:5 day:31 month:12 https://dx.doi.org/10.1007/s11704-020-9294-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2005 AR 15 2020 5 31 12 |
| allfieldsGer |
10.1007/s11704-020-9294-7 doi (DE-627)SPR05114851X (SPR)s11704-020-9294-7-e DE-627 ger DE-627 rakwb eng Sun, Yan-Ping verfasserin aut Compositional metric learning for multi-label classification 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Higher Education Press 2020 Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. machine learning (dpeaa)DE-He213 multi-label learning (dpeaa)DE-He213 metric learning (dpeaa)DE-He213 compositional metric (dpeaa)DE-He213 positive semidefinite matrix decomposition (dpeaa)DE-He213 Zhang, Min-Ling aut Enthalten in Frontiers of computer science in China Beijing : Higher Education Press, 2007 15(2020), 5 vom: 31. Dez. (DE-627)545787726 (DE-600)2388878-7 1673-7466 nnns volume:15 year:2020 number:5 day:31 month:12 https://dx.doi.org/10.1007/s11704-020-9294-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2005 AR 15 2020 5 31 12 |
| allfieldsSound |
10.1007/s11704-020-9294-7 doi (DE-627)SPR05114851X (SPR)s11704-020-9294-7-e DE-627 ger DE-627 rakwb eng Sun, Yan-Ping verfasserin aut Compositional metric learning for multi-label classification 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Higher Education Press 2020 Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. machine learning (dpeaa)DE-He213 multi-label learning (dpeaa)DE-He213 metric learning (dpeaa)DE-He213 compositional metric (dpeaa)DE-He213 positive semidefinite matrix decomposition (dpeaa)DE-He213 Zhang, Min-Ling aut Enthalten in Frontiers of computer science in China Beijing : Higher Education Press, 2007 15(2020), 5 vom: 31. Dez. (DE-627)545787726 (DE-600)2388878-7 1673-7466 nnns volume:15 year:2020 number:5 day:31 month:12 https://dx.doi.org/10.1007/s11704-020-9294-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2005 AR 15 2020 5 31 12 |
| language |
English |
| source |
Enthalten in Frontiers of computer science in China 15(2020), 5 vom: 31. Dez. volume:15 year:2020 number:5 day:31 month:12 |
| sourceStr |
Enthalten in Frontiers of computer science in China 15(2020), 5 vom: 31. Dez. volume:15 year:2020 number:5 day:31 month:12 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
machine learning multi-label learning metric learning compositional metric positive semidefinite matrix decomposition |
| isfreeaccess_bool |
false |
| container_title |
Frontiers of computer science in China |
| authorswithroles_txt_mv |
Sun, Yan-Ping @@aut@@ Zhang, Min-Ling @@aut@@ |
| publishDateDaySort_date |
2020-12-31T00:00:00Z |
| hierarchy_top_id |
545787726 |
| id |
SPR05114851X |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR05114851X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230509120556.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230508s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11704-020-9294-7</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR05114851X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s11704-020-9294-7-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Sun, Yan-Ping</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Compositional metric learning for multi-label classification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Higher Education Press 2020</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">machine learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">multi-label learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">metric learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">compositional metric</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">positive semidefinite matrix decomposition</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Min-Ling</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Frontiers of computer science in China</subfield><subfield code="d">Beijing : Higher Education Press, 2007</subfield><subfield code="g">15(2020), 5 vom: 31. Dez.</subfield><subfield code="w">(DE-627)545787726</subfield><subfield code="w">(DE-600)2388878-7</subfield><subfield code="x">1673-7466</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:15</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:5</subfield><subfield code="g">day:31</subfield><subfield code="g">month:12</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s11704-020-9294-7</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_138</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_250</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_281</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">15</subfield><subfield code="j">2020</subfield><subfield code="e">5</subfield><subfield code="b">31</subfield><subfield code="c">12</subfield></datafield></record></collection>
|
| author |
Sun, Yan-Ping |
| spellingShingle |
Sun, Yan-Ping misc machine learning misc multi-label learning misc metric learning misc compositional metric misc positive semidefinite matrix decomposition Compositional metric learning for multi-label classification |
| authorStr |
Sun, Yan-Ping |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)545787726 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
1673-7466 |
| topic_title |
Compositional metric learning for multi-label classification machine learning (dpeaa)DE-He213 multi-label learning (dpeaa)DE-He213 metric learning (dpeaa)DE-He213 compositional metric (dpeaa)DE-He213 positive semidefinite matrix decomposition (dpeaa)DE-He213 |
| topic |
misc machine learning misc multi-label learning misc metric learning misc compositional metric misc positive semidefinite matrix decomposition |
| topic_unstemmed |
misc machine learning misc multi-label learning misc metric learning misc compositional metric misc positive semidefinite matrix decomposition |
| topic_browse |
misc machine learning misc multi-label learning misc metric learning misc compositional metric misc positive semidefinite matrix decomposition |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Frontiers of computer science in China |
| hierarchy_parent_id |
545787726 |
| hierarchy_top_title |
Frontiers of computer science in China |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)545787726 (DE-600)2388878-7 |
| title |
Compositional metric learning for multi-label classification |
| ctrlnum |
(DE-627)SPR05114851X (SPR)s11704-020-9294-7-e |
| title_full |
Compositional metric learning for multi-label classification |
| author_sort |
Sun, Yan-Ping |
| journal |
Frontiers of computer science in China |
| journalStr |
Frontiers of computer science in China |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2020 |
| contenttype_str_mv |
txt |
| author_browse |
Sun, Yan-Ping Zhang, Min-Ling |
| container_volume |
15 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Sun, Yan-Ping |
| doi_str_mv |
10.1007/s11704-020-9294-7 |
| title_sort |
compositional metric learning for multi-label classification |
| title_auth |
Compositional metric learning for multi-label classification |
| abstract |
Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. © Higher Education Press 2020 |
| abstractGer |
Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. © Higher Education Press 2020 |
| abstract_unstemmed |
Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification. © Higher Education Press 2020 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2005 |
| container_issue |
5 |
| title_short |
Compositional metric learning for multi-label classification |
| url |
https://dx.doi.org/10.1007/s11704-020-9294-7 |
| remote_bool |
true |
| author2 |
Zhang, Min-Ling |
| author2Str |
Zhang, Min-Ling |
| ppnlink |
545787726 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11704-020-9294-7 |
| up_date |
2024-07-03T20:05:05.295Z |
| _version_ |
1803589627728101376 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR05114851X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230509120556.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230508s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11704-020-9294-7</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR05114851X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s11704-020-9294-7-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Sun, Yan-Ping</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Compositional metric learning for multi-label classification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Higher Education Press 2020</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">machine learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">multi-label learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">metric learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">compositional metric</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">positive semidefinite matrix decomposition</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Min-Ling</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Frontiers of computer science in China</subfield><subfield code="d">Beijing : Higher Education Press, 2007</subfield><subfield code="g">15(2020), 5 vom: 31. Dez.</subfield><subfield code="w">(DE-627)545787726</subfield><subfield code="w">(DE-600)2388878-7</subfield><subfield code="x">1673-7466</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:15</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:5</subfield><subfield code="g">day:31</subfield><subfield code="g">month:12</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s11704-020-9294-7</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_138</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_250</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_281</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">15</subfield><subfield code="j">2020</subfield><subfield code="e">5</subfield><subfield code="b">31</subfield><subfield code="c">12</subfield></datafield></record></collection>
|
| score |
7.4009523 |