A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
[Uczenie maszynowe] Autorzy: Fred Xu, Thomas Markovich, Florence Regol i 1 więcej
Reliable deployment of graph neural networks requires calibration, out-of-distribution (OOD) detection, and robustness to distribution shift, yet existing methods address these needs with separate models and objectives. We model uncertain node embeddings as random graph signals: graph Fourier filters capture structural variation, and a scalar orthogonal-polynomial chaos coordinate captures latent stochastic variation. The resulting doubly-spectral stochastic (DSS) expansion supplies task-matched readouts from one representation: the mean coefficient encodes class evidence for the energy-based OOD score, the higher-order coefficients encode structured logit variation, and quadrature averaging over the chaos coordinate defines the single predictive distribution used for prediction and calibration. A capacity theorem shows that, under a full-rank feature assumption, a restricted subfamily …
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe