Unsupervised Graph Neural Network Modeling: A New Framework for Accounting Account Anomaly Detection
A latest arXiv paper proposes an unsupervised discriminative framework based on graph neural networks that abstracts acc…
🏷️ Graph Neural Network
3 articles about 'Graph Neural Network'
MomentumGNN: A New Graph Neural Network Architecture with Built-In Conservation of Momentum
Researchers propose MomentumGNN, a novel architecture that embeds momentum conservation constraints directly into graph …
Study Reveals Mini-Batch Class Composition Bias in Link Prediction
A latest arXiv paper discovers that graph neural networks introduce class composition bias through mini-batch training s…
1