On Measuring Intrinsic Causal Attributions in Deep Neural Networks
This work addresses the need for better interpretability in deep learning for researchers and practitioners, though it appears incremental by extending existing causal frameworks.
The paper tackled the problem of quantifying causal influence of input features in neural networks by introducing intrinsic causal contributions (ICC) as a new measure, and demonstrated that ICC provides more intuitive and reliable explanations than existing methods in experiments on synthetic and real-world datasets.
Quantifying the causal influence of input features within neural networks has become a topic of increasing interest. Existing approaches typically assess direct, indirect, and total causal effects. This work treats NNs as structural causal models (SCMs) and extends our focus to include intrinsic causal contributions (ICC). We propose an identifiable generative post-hoc framework for quantifying ICC. We also draw a relationship between ICC and Sobol' indices. Our experiments on synthetic and real-world datasets demonstrate that ICC generates more intuitive and reliable explanations compared to existing global explanation techniques.