LocalGLMnet: interpretable deep learning for tabular data
This addresses the need for interpretable deep learning models in statistical modeling, particularly for tabular data, though it is incremental as it builds on existing generalized linear model structures.
The authors tackled the problem of interpretability in deep learning for tabular data by proposing LocalGLMnet, a new network architecture inspired by generalized linear models, which achieved superior predictive power while enabling variable selection and interpretation through an additive decomposition similar to Shapley values.
Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep learning models is that their solutions are difficult to interpret and explain, and variable selection is not easily possible because deep learning models solve feature engineering and variable selection internally in a nontransparent way. Inspired by the appealing structure of generalized linear models, we propose a new network architecture that shares similar features as generalized linear models, but provides superior predictive power benefiting from the art of representation learning. This new architecture allows for variable selection of tabular data and for interpretation of the calibrated deep learning model, in fact, our approach provides an additive decomposition in the spirit of Shapley values and integrated gradients.