Jaringan Saraf Graf Boleh Dijelas
Jaringan Saraf Graf Boleh Dijelas (XAI-GNN) menggabungkan seni bina GNN standard dengan teknik penjelasan pasca-hoc atau intrinsik yang mendedahkan nod, tepi, dan ciri nod mana yang mendorong ramalan model. Dipelopori oleh GNNExplainer (Ying et al., 2019), bidang ini menangani kritikan kotak hitam GNN dan penting di mana sahaja ramalan berasaskan graf perlu dipercayai atau diaudit.
Baca kaedah sepenuhnya
Log masuk dengan akaun percuma untuk membaca bahagian ini.
Method map
The neighbourhood of related methods — select a node to explore.
Sumber
- Ying, Z., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019). GNNExplainer: Generating Explanations for Graph Neural Networks. Advances in Neural Information Processing Systems (NeurIPS), 32, 9240–9251. link ↗
- Yuan, H., Yu, H., Gui, S., & Ji, S. (2023). Explainability in Graph Neural Networks: A Taxonomic Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5782–5799. DOI: 10.1109/TPAMI.2022.3204236 ↗
Cara memetik halaman ini
ScholarGate. (2026, June 3). Explainable Graph Neural Network (XAI-GNN). ScholarGate. https://scholargate.app/ms/deep-learning/explainable-graph-neural-network
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Klasifikasi Berasaskan BERT yang Boleh DijelaskanPembelajaran Mendalam↔ compare
- Transformer Boleh DijelaskanPembelajaran Mendalam↔ compare
- Graph Neural NetworkAnalisis Rangkaian↔ compare
Terjumpa masalah pada halaman ini? Laporkan atau cadangkan pembetulan →