XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
This addresses the need for interpretable machine learning in data-driven applications where transparency is crucial, representing an incremental improvement by combining existing techniques.
The authors tackled the problem of interpretability in neural networks for tabular data by developing XNNTab, which uses sparse autoencoders to decompose features into interpretable concepts, achieving performance comparable to non-interpretable models.
In data-driven applications relying on tabular data, where interpretability is key, machine learning models such as decision trees and linear regression are applied. Although neural networks can provide higher predictive performance, they are not used because of their blackbox nature. In this work, we present XNNTab, a neural architecture that combines the expressiveness of neural networks and interpretability. XNNTab first learns highly non-linear feature representations, which are decomposed into monosemantic features using a sparse autoencoder (SAE). These features are then assigned human-interpretable concepts, making the overall model prediction intrinsically interpretable. XNNTab outperforms interpretable predictive models, and achieves comparable performance to its non-interpretable counterparts.