Search papers, labs, and topics across Lattice.
The paper introduces Neural Additive Experts (NAEs), a mixture-of-experts framework that learns specialized networks per feature and uses a dynamic gating mechanism to integrate information across features, relaxing the strict additivity of standard GAMs. NAEs address the trade-off between interpretability and accuracy by allowing for controlled feature interactions while maintaining clarity in feature attributions through targeted regularization. Experiments on synthetic and real-world datasets demonstrate that NAEs achieve a better balance between predictive accuracy and feature-level explanations compared to standard GAMs.
Achieve GAM-level interpretability with deep learning accuracy by dynamically gating feature interactions through a mixture of experts.
The trade-off between interpretability and accuracy remains a core challenge in machine learning. Standard Generalized Additive Models (GAMs) offer clear feature attributions but are often constrained by their strictly additive nature, which can limit predictive performance. Introducing feature interactions can boost accuracy yet may obscure individual feature contributions. To address these issues, we propose Neural Additive Experts (NAEs), a novel framework that seamlessly balances interpretability and accuracy. NAEs employ a mixture of experts framework, learning multiple specialized networks per feature, while a dynamic gating mechanism integrates information across features, thereby relaxing rigid additive constraints. Furthermore, we propose targeted regularization techniques to mitigate variance among expert predictions, facilitating a smooth transition from an exclusively additive model to one that captures intricate feature interactions while maintaining clarity in feature attributions. Our theoretical analysis and experiments on synthetic data illustrate the model's flexibility, and extensive evaluations on real-world datasets confirm that NAEs achieve an optimal balance between predictive accuracy and transparent, feature-level explanations. The code is available at https://github.com/Teddy-XiongGZ/NAE.
