Spectral Graph Conditional Exchangeability
Spectral Graph Conditional Exchangeability
Auto-generated stub. Edit this file to add more details.
A framework for uncertainty quantification in non-exchangeable graph-structured data by conditioning high-frequency spectral components on low-frequency global trends.
Why It Matters
Introduces a novel paradigm for applying conformal prediction to non-exchangeable graph-structured time series by conditioning on spectral features.
Evidence
propose a novel concept named Spectral Graph Conditional Exchangeability (SGCE), which conditions exchangeable high-frequency components on low-frequency ones to preserve global trends and enable effective CP in the spectral domain.
Related Papers
Metadata & Links
- created_at
- 2026-05-09T05:56:47Z