GIN · full_fcg
Standard SplitFeb 17, 2026d790cb53338f4e109fbfc6c3e41744cf
Description
Train GIN on the full_fcg dataset (all methods, internal + external) to compare with the internal_only result from Experiment 02.
Conclusion
Lower accuracy than internal_only (95.4% vs 98.2%) despite the richer graph representation. Still achieves perfect malware recall. Suggests the larger graphs introduce noise without improving discriminative power for GIN.
Test Metrics
Accuracy
95.4%
F1 Macro
94.7%
F1 Malware
92.8%
Precision
86.5%
Recall
100.0%
AUROC
97.7%
Best Val Loss
0.0935
Training Time
935.0000s
Confusion Matrix
| Pred Benign | Pred Malware | |
|---|---|---|
| Actual Benign | 71 | 5 |
| Actual Malware | 0 | 32 |
Configuration
| Hidden Dim | 128 |
| Num Layers | 3 |
| Dropout | 0.5 |
| Batch Size | 4 |
| Learning Rate | 0.001 |
| Weight Decay | 0.0001 |
| Max Epochs | 200 |
| ES Patience | 20 |
| ES Min Epochs | 100 |
| LR Patience | 10 |
| LR Factor | 0.5 |
| Mixed Precision | Yes |
| Random Seed | 42 |
| Epochs Trained | 113 |