SHAPNN: Shapley Value Regularized Tabular Neural Network
This work addresses the need for more interpretable and robust neural networks in tabular data applications, though it appears incremental by combining existing techniques.
The authors tackled the problem of improving deep tabular data models by integrating Shapley values for explanation, resulting in enhanced performance in AUROC, transparency, and robustness to streaming data across various datasets.
We present SHAPNN, a novel deep tabular data modeling architecture designed for supervised learning. Our approach leverages Shapley values, a well-established technique for explaining black-box models. Our neural network is trained using standard backward propagation optimization methods, and is regularized with realtime estimated Shapley values. Our method offers several advantages, including the ability to provide valid explanations with no computational overhead for data instances and datasets. Additionally, prediction with explanation serves as a regularizer, which improves the model's performance. Moreover, the regularized prediction enhances the model's capability for continual learning. We evaluate our method on various publicly available datasets and compare it with state-of-the-art deep neural network models, demonstrating the superior performance of SHAPNN in terms of AUROC, transparency, as well as robustness to streaming data.