New method calibrates graph neural networks using interpretable structural temperature scaling
A new arXiv paper proposes interpretable structural temperature scaling to calibrate graph neural networks and point-cloud segmentation, predicting per-node temperatures with graph-aware calibrators.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv cs.LG
Interpretable structural temperature scaling for calibrating graph neural networks and point-cloud segmentation