Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
This addresses the problem of maintaining interpretability while improving accuracy for users of additive models, though it is incremental by building on Generalized Additive Models with novel gating and regularization.
The paper tackles the trade-off between interpretability and accuracy in machine learning by proposing Neural Additive Experts (NAEs), a framework that balances these aspects through a mixture of experts with dynamic gating and targeted regularization, achieving an optimal balance as confirmed by experiments on real-world datasets.
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.