no code implementations • 14 Feb 2022 • Yufan Zeng, Jiashan Tang
However, we spot three issues of RLC-GNN, which are the usage of neighboring information reaching limitation, the training difficulty which is inherent problem to deep models and lack of comprehensive consideration about node features and external patterns.
no code implementations • Applied Sciences 2021 • Yufan Zeng, Jiashan Tang
As the single-layer CARE-GNN cannot extract more information to fix the potential mistakes, the performance heavily relies on the only one layer.
Ranked #2 on Fraud Detection on Amazon-Fraud