Gaussian Process Neural Additive Models
This work addresses interpretability challenges in deep learning for tabular data, offering a more efficient and convex alternative, though it is incremental as it builds on existing Neural Additive Models.
The paper tackles the need for interpretable deep learning in fields like healthcare and finance by proposing Gaussian Process Neural Additive Models (GP-NAM), which achieve comparable or better performance in classification and regression tasks with a large reduction in parameters compared to deeper NAM approaches.
Deep neural networks have revolutionized many fields, but their black-box nature also occasionally prevents their wider adoption in fields such as healthcare and finance, where interpretable and explainable models are required. The recent development of Neural Additive Models (NAMs) is a significant step in the direction of interpretable deep learning for tabular datasets. In this paper, we propose a new subclass of NAMs that use a single-layer neural network construction of the Gaussian process via random Fourier features, which we call Gaussian Process Neural Additive Models (GP-NAM). GP-NAMs have the advantage of a convex objective function and number of trainable parameters that grows linearly with feature dimensionality. It suffers no loss in performance compared to deeper NAM approaches because GPs are well-suited for learning complex non-parametric univariate functions. We demonstrate the performance of GP-NAM on several tabular datasets, showing that it achieves comparable or better performance in both classification and regression tasks with a large reduction in the number of parameters.