Towards Robust Interpretability with Self-Explaining Neural Networks
This work addresses the need for more robust and interpretable models in AI, offering a novel approach that could benefit applications requiring transparency, though it appears incremental in advancing existing interpretability methods.
The paper tackles the problem of interpretability in machine learning by proposing self-explaining neural networks that integrate interpretability during learning, rather than post-hoc, and demonstrates their effectiveness across benchmark datasets.
Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where interpretability plays a key role already during learning have received much less attention. We propose three desiderata for explanations in general -- explicitness, faithfulness, and stability -- and show that existing methods do not satisfy them. In response, we design self-explaining models in stages, progressively generalizing linear classifiers to complex yet architecturally explicit models. Faithfulness and stability are enforced via regularization specifically tailored to such models. Experimental results across various benchmark datasets show that our framework offers a promising direction for reconciling model complexity and interpretability.