A Neural Network Alternative to Tree-based Models
This addresses the need for more interpretable and high-performing neural networks in scientific domains like biology, offering an incremental improvement over existing methods.
The paper tackled the problem of neural networks underperforming tree-based models on tabular data by proposing sTAB-Net, which uses attention mechanisms to enforce sparsity, achieving state-of-the-art performance on biological datasets and outperforming methods like SHAP.
Tabular datasets are widely used in scientific disciplines such as biology. While these disciplines have already adopted AI methods to enhance their findings and analysis, they mainly use tree-based methods due to their interpretability. At the same time, artificial neural networks have been shown to offer superior flexibility and depth for rich and complex non-tabular problems, but they are falling behind tree-based models for tabular data in terms of performance and interpretability. Although sparsity has been shown to improve the interpretability and performance of ANN models for complex non-tabular datasets, enforcing sparsity structurally and formatively for tabular data before training the model, remains an open question. To address this question, we establish a method that infuses sparsity in neural networks by utilising attention mechanisms to capture the features' importance in tabular datasets. We show that our models, Sparse TABular NET or sTAB-Net with attention mechanisms, are more effective than tree-based models, reaching the state-of-the-art on biological datasets. They further permit the extraction of insights from these datasets and achieve better performance than post-hoc methods like SHAP.