Improvement of Attention Mechanism Explainability in Prediction of Chemical Molecules’ Properties
Ładowanie...
Data
2023
Autorzy
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
In 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.
Opis
Słowa kluczowe
attention mechanism, graph transformer, graph neural network, explainability, chemical molecules, mechanizm uwagi, transformator grafowy, grafowa sieć neuronowa, wyjaśnialność, cząsteczki chemiczne
Cytowanie
Durys 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.