Interpretable Graph Neural Networks for Heterogeneous Tabular Data
This addresses the need for interpretability in machine learning for tabular data, though it is incremental as it builds on existing graph neural network methods.
The authors tackled the problem of black-box models in tabular data by proposing IGNH, an interpretable graph neural network that handles heterogeneous features and provides exact feature attributions, achieving performance comparable to XGBoost and outperforming Random Forests and TabNet.
Many machine learning algorithms for tabular data produce black-box models, which prevent users from understanding the rationale behind the model predictions. In their unconstrained form, graph neural networks fall into this category, and they have further limited abilities to handle heterogeneous data. To overcome these limitations, an approach is proposed, called IGNH (Interpretable Graph Neural Network for Heterogeneous tabular data), which handles both categorical and numerical features, while constraining the learning process to generate exact feature attributions together with the predictions. A large-scale empirical investigation is presented, showing that the feature attributions provided by IGNH align with Shapley values that are computed post hoc. Furthermore, the results show that IGNH outperforms two powerful machine learning algorithms for tabular data, Random Forests and TabNet, while reaching a similar level of performance as XGBoost.