SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths
Quick summary
arXiv:2606.09404v2 Announce Type: replace-cross Abstract: Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types. We propose Surrogate-based Analysis of Interactions via Local Effect Smooths (SAILS), a model-agnostic framework that analyzes pairwise interactions through generalized additive model (GAM) surrogates fitted to the local effects of a black-box model. For each interval of a feature of interest, the
Key takeaways
- arXiv:2606.09404v2 Announce Type: replace-cross Abstract: Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types.
- We propose Surrogate-based Analysis of Interactions via Local Effect Smooths (SAILS), a model-agnostic framework that analyzes pairwise interactions through generalized additive model (GAM) surrogates fitted to the local effects of a black-box model.
- For each interval of a feature of interest, the
Why it matters
“SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments