دورية أكاديمية

Neural Architecture Search for GNN-Based Graph Classification.

التفاصيل البيبلوغرافية
العنوان: Neural Architecture Search for GNN-Based Graph Classification.
المؤلفون: LANNING WEI, HUAN ZHAO, ZHIQIANG HE, QUANMING YAO
المصدر: ACM Transactions on Information Systems; Jan2024, Vol. 42 Issue 1, p1-29, 29p
مستخلص: The article focuses on addressing the challenge of designing adaptive pooling architectures for graph classification by using neural architecture search (NAS). Topics include the development of Pooling Architecture Search (PAS) for designing pooling architectures, the two variants such as PAS-G and PAS-NE for designing pooling operations in different scales, and the experiments on real-world datasets to demonstrate the effectiveness and efficiency of PAS in improving graph classification.
قاعدة البيانات: Complementary Index