Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability

ICLR 2026 Conference Submission21420 Authors

Keywords: Interpretable deep learning, feature selection, High-dimensional data analysis

TL;DR: Sparse Deep Additive Model with Interactions (SDAMI)

Abstract: Recent advances in deep learning highlight the need for personalized models that can learn from small or moderate samples, handle high-dimensional features, and remain interpretable. To address this challenge, we propose the Sparse Deep Additive Model with Interactions (SDAMI), a framework that combines sparsity-driven feature selection with deep subnetworks for flexible function approximation. Unlike conventional deep learning models, which often function as black boxes, SDAMI explicitly disentangles main effects and interaction effects to enhance interpretability. At the same time, its deep additive structure achieves higher predictive accuracy than classical additive models. Central to SDAMI is the concept of an Effect Footprint, which assumes that higher-order interactions project marginally onto main effects. Guided by this principle, SDAMI adopts a two-stage strategy: first, identify strong main effects that implicitly carry information about important interactions; second, exploit this information—through structured regularization such as group lasso—to distinguish genuine main effects from interaction effects. For each selected main effect, SDAMI constructs a dedicated subnetwork, enabling nonlinear function approximation while preserving interpretability and providing a structured foundation for modeling interactions. Extensive simulations with comparisons confirm SDAMI’s ability to recover effect structures across diverse scenarios. Applications in reliability analysis, neuroscience, and medical diagnostics further demonstrate its versatility in addressing real-world high-dimensional modeling challenges.

Primary Area: interpretability and explainable AI

Submission Number: 21420