Accurate graph classification via two-staged contrastive curriculum learning
Copyright: © 2024 Shim et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited..
Given a graph dataset, how can we generate meaningful graph representations that maximize classification accuracy? Learning representative graph embeddings is important for solving various real-world graph-based tasks. Graph contrastive learning aims to learn representations of graphs by capturing the relationship between the original graph and the augmented graph. However, previous contrastive learning methods neither capture semantic information within graphs nor consider both nodes and graphs while learning graph embeddings. We propose TAG (Two-staged contrAstive curriculum learning for Graphs), a two-staged contrastive learning method for graph classification. TAG learns graph representations in two levels: node-level and graph level, by exploiting six degree-based model-agnostic augmentation algorithms. Experiments show that TAG outperforms both unsupervised and supervised methods in classification accuracy, achieving up to 4.08% points and 4.76% points higher than the second-best unsupervised and supervised methods on average, respectively.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:19 |
---|---|
Enthalten in: |
PloS one - 19(2024), 1 vom: 31., Seite e0296171 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Shim, Sooyeon [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 05.01.2024 Date Revised 06.01.2024 published: Electronic-eCollection Citation Status MEDLINE |
---|
doi: |
10.1371/journal.pone.0296171 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM366613391 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM366613391 | ||
003 | DE-627 | ||
005 | 20240108142639.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240108s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1371/journal.pone.0296171 |2 doi | |
028 | 5 | 2 | |a pubmed24n1250.xml |
035 | |a (DE-627)NLM366613391 | ||
035 | |a (NLM)38170711 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Shim, Sooyeon |e verfasserin |4 aut | |
245 | 1 | 0 | |a Accurate graph classification via two-staged contrastive curriculum learning |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 05.01.2024 | ||
500 | |a Date Revised 06.01.2024 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright: © 2024 Shim et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. | ||
520 | |a Given a graph dataset, how can we generate meaningful graph representations that maximize classification accuracy? Learning representative graph embeddings is important for solving various real-world graph-based tasks. Graph contrastive learning aims to learn representations of graphs by capturing the relationship between the original graph and the augmented graph. However, previous contrastive learning methods neither capture semantic information within graphs nor consider both nodes and graphs while learning graph embeddings. We propose TAG (Two-staged contrAstive curriculum learning for Graphs), a two-staged contrastive learning method for graph classification. TAG learns graph representations in two levels: node-level and graph level, by exploiting six degree-based model-agnostic augmentation algorithms. Experiments show that TAG outperforms both unsupervised and supervised methods in classification accuracy, achieving up to 4.08% points and 4.76% points higher than the second-best unsupervised and supervised methods on average, respectively | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Kim, Junghun |e verfasserin |4 aut | |
700 | 1 | |a Park, Kahyun |e verfasserin |4 aut | |
700 | 1 | |a Kang, U |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t PloS one |d 2006 |g 19(2024), 1 vom: 31., Seite e0296171 |w (DE-627)NLM167327399 |x 1932-6203 |7 nnns |
773 | 1 | 8 | |g volume:19 |g year:2024 |g number:1 |g day:31 |g pages:e0296171 |
856 | 4 | 0 | |u http://dx.doi.org/10.1371/journal.pone.0296171 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 19 |j 2024 |e 1 |b 31 |h e0296171 |