Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
arXiv:2610.22126v1 Announce Type: cross Abstract: Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which extend integrated gradients to incorporate prior caus…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-19 04:00 · arXiv stat.ML
Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths