Neural Information Processing Systems http://nips.cc/

Most recent work on interpretability of complex machine learning models has focused on estimating a-posteriori explanations for previously trained models around specific predictions. 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.

Summary: The paper proposes an alternative approach to obtaining explanations from complex ML algorithms by aiming to produce an explainable modle from the start. Recently there has been a number of works on interpretability. This work is most similar to concept-based explainability where some of the more recent ones include • Bau, David, et al. "Network Dissection: Quantifying Interpretability of Deep Visual Representations." It starts out with a linear regression model and replaces the parameters of the model with a function dependent on the input, adds an optional transformation of the input into a more low-dimensional space and a generalization of the aggregration into the output. The main novelty of this paper is the idea to start out with an intrinsically interpretable model and extending it.

Complex deep learning models show high prediction tasks in various clinical prediction tasks but their inherent complexity makes it more challenging to explain model predictions for clinicians and healthcare providers. Existing research on explainability of deep learning models in healthcare have two major limitations: using post-hoc explanations and using raw clinical variables as units of explanation, both of which are often difficult for human interpretation. In this work, we designed a self-explaining deep learning framework using the expert-knowledge driven clinical concepts or intermediate features as units of explanation. The self-explaining nature of our proposed model comes from generating both explanations and predictions within the same architectural framework via joint training. We tested our proposed approach on a publicly available Electronic Health Records (EHR) dataset for predicting patient mortality in the ICU. In order to analyze the performance-interpretability trade-off, we compared our proposed model with a baseline having the same set-up but without the explanation components. Experimental results suggest that adding explainability components to a deep learning framework does not impact prediction performance and the explanations generated by the model can provide insights to the clinicians to understand the possible reasons behind patient mortality.

Most recent work on interpretability of complex machine learning models has focused on estimating a-posteriori explanations for previously trained models around specific predictions. 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. 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.