Reproducible research comparing GNN (GraphSAGE, GCN, GAT) vs ML baselines (XGBoost, RF) on Elliptic++ Bitcoin fraud detection. Features ablation experiments revealing when tabular models outperform graph neural networks.
machine-learning bitcoin reproducible-research pytorch cryptocurrency xgboost feature-engineering fraud-detection graphsage graph-neural-networks pytorch-geometric temporal-graphs ablation-study elliptic-dataset temporal-split
-
Updated
Nov 8, 2025 - Python