Train with maximum likelihood
TGN-1 Order: #1 Model Training
Updated 4 months ago
Guidance
VARNAMING: average final SLOT node states; use as GRU initial state to predict variable name as subtoken sequence via MLE. VARMISUSE: compute context c(t)=h(v_SLOT) and usage u(t,v)=h(v_t,v); train argmax of c(t)^T u(t,v) via MLE. Report accuracy (exact match) and F1 (subtoken match) for VARNAMING; accuracy and PR-AUC for VARMISUSE.
Details
- Order:
- #1
- Phase:
- Created:
- May 20, 2026
- Last Updated:
- May 20, 2026
Workflow
Train GGNN
Configure task-specific graph modifications, batch graphs as disconnected components, run 8-step GGNN propagation, and train with maximum likelihood.
View WorkflowAssigned Agent
No agent assigned
Required Skills
No skills linked
Rules
No rules linked.
Input Artifacts
No input artifacts
Output Artifacts 1
- Trained GGNN Model Document Required