Improvement of Attention Mechanism Explainability in Prediction of Chemical Molecules’ Properties

Uproszczony widok
dc.contributor.authorDurys, Bartosz
dc.contributor.authorTomczyk, Arkadiusz
dc.date.accessioned2023-09-21T10:25:36Z
dc.date.available2023-09-21T10:25:36Z
dc.date.issued2023
dc.description.abstractIn this paper, the analysis of selected graph neural network operators is presented. The classic Graph Convolutional Network (GCN) was compared with methods containing trainable attention coefficients: Graph Attention Network (GAT) and Graph Transformer (GT). Moreover, which is an original contribution of this work, training of GT was modified with an additional loss function component enabling easier explainability of the produced model. The experiments were conducted using datasets with chemical molecules where both classification and regression tasks are considered. The results show that additional constraint not only does not make the results worse but, in some cases, it improves predictions.en_EN
dc.identifier.citationDurys B., Tomczyk A., Improvement of Attention Mechanism Explainability in Prediction of Chemical Molecules’ Properties. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 119-124, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.17.
dc.identifier.doi10.34658/9788366741928.17
dc.identifier.isbn978-83-66741-92-8
dc.identifier.urihttp://hdl.handle.net/11652/4792
dc.identifier.urihttps://doi.org/10.34658/9788366741928.17
dc.language.isoenen_EN
dc.page.numbers. 119-124
dc.publisherWydawnictwo Politechniki Łódzkiejpl_PL
dc.publisherLodz University of Technology Pressen_EN
dc.relation.ispartofWojciechowski A. (Ed.), Lipiński P. (Ed.)., Progress in Polish Artificial Intelligence Research 4, Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.
dc.rightsDla wszystkich w zakresie dozwolonego użytkupl_PL
dc.rightsFair use conditionen_EN
dc.rights.licenseLicencja PŁpl_PL
dc.rights.licenseLUT Licenseen_EN
dc.subjectattention mechanismen_EN
dc.subjectgraph transformeren_EN
dc.subjectgraph neural networken_EN
dc.subjectexplainabilityen_EN
dc.subjectchemical moleculesen_EN
dc.subjectmechanizm uwagipl_PL
dc.subjecttransformator grafowypl_PL
dc.subjectgrafowa sieć neuronowapl_PL
dc.subjectwyjaśnialnośćpl_PL
dc.subjectcząsteczki chemicznepl_PL
dc.titleImprovement of Attention Mechanism Explainability in Prediction of Chemical Molecules’ Propertiesen_EN
dc.typeRozdział - monografiapl_PL
dc.typeChapter - monographen_EN

Pliki

Oryginalne pliki
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
17. Improv_attent_mechan_Durys_Tomczyk_2023.pdf
Rozmiar:
252.77 KB
Format:
Adobe Portable Document Format
Opis:
Pobierz
Licencja
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
license.txt
Rozmiar:
1.71 KB
Format:
Item-specific license agreed upon to submission
Opis:
Pobierz

Kolekcje

Rozdziały
Książki, monografie, podręczniki, rozdziały (WFTIiMS)