A Model of Causal Explanation on Neural Networks for Tabular Data
This work addresses the need for interpretable AI in high-stakes domains like healthcare or finance by providing causal explanations for neural network predictions on tabular data, though it appears incremental as it builds on existing explanation methods.
The study tackled the problem of explaining neural network predictions on tabular data by addressing pseudo-correlation and causality issues, proposing CENNET, a causal explanation method combined with structural causal models, and showing its effectiveness through comparative experiments on synthetic and quasi-real data in classification tasks.
The problem of explaining the results produced by machine learning methods continues to attract attention. Neural network (NN) models, along with gradient boosting machines, are expected to be utilized even in tabular data with high prediction accuracy. This study addresses the related issues of pseudo-correlation, causality, and combinatorial reasons for tabular data in NN predictors. We propose a causal explanation method, CENNET, and a new explanation power index using entropy for the method. CENNET provides causal explanations for predictions by NNs and uses structural causal models (SCMs) effectively combined with the NNs although SCMs are usually not used as predictive models on their own in terms of predictive accuracy. We show that CEN-NET provides such explanations through comparative experiments with existing methods on both synthetic and quasi-real data in classification tasks.