Julia Herbinger

This framework introduces kernel-based output representations that enable time-dependency-aware explanations at multiple levels of temporal granularity, including time-specific, time-resolved, and time-aggregated, while providing a unified view in which existing methods arise as special cases.

SAILS reveals the functional forms of feature interactions in machine learning models, transforming how we interpret model behavior beyond mere detection.

Additive explanations of survival models fail because of their inherent non-additivity, but now there's a way to decompose feature interactions into time-dependent components to understand *when* and *why* they fail.