A Model of Causal Explanation on Neural Networks for Tabular Data

TL;DR

This paper introduces CENNET, a causal explanation method for neural networks on tabular data, combining structural causal models with neural networks to improve interpretability and address pseudo-correlation issues.

Contribution

It proposes a novel causal explanation technique, CENNET, and an entropy-based explanation power index, enhancing interpretability of neural networks for tabular data.

Findings

CENNET effectively provides causal explanations for neural network predictions.

The method outperforms existing explanation techniques in experiments.

CENNET successfully addresses pseudo-correlation and causality issues.

Abstract

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.