A masked graph autoencoder on heterogeneous bidirectional graphs predicts per-flow NetFlow attachments and features from sliding windows of network traffic.
Scikit-learn: Machine learning in Python,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A data-driven pipeline reduces EIS measurements by 99% and achieves 80% accuracy with AUC 0.90 for healthy vs. cancer classification plus AUCs above 0.82 in multi-class oral lesion tasks using leave-one-patient-group-out validation.
citing papers explorer
-
Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder
A masked graph autoencoder on heterogeneous bidirectional graphs predicts per-flow NetFlow attachments and features from sliding windows of network traffic.
-
Optimizing In Vivo Oral Lesion Classification from Electrical Impedance Spectroscopy Using Data-driven Approaches
A data-driven pipeline reduces EIS measurements by 99% and achieves 80% accuracy with AUC 0.90 for healthy vs. cancer classification plus AUCs above 0.82 in multi-class oral lesion tasks using leave-one-patient-group-out validation.