Local Evidence and Geometric Readout Repair in Trained GNNs
arXiv:2609.27092v1 Announce Type: new Abstract: Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights or a reachable logit set poorly positioned for the classifier. We separate these causes with an exact-…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.LG
Local Evidence and Geometric Readout Repair in Trained GNNs