Interpretable by Design: Learning Predictors by Composing Interpretable Queries
This addresses the need for interpretable AI in risk-sensitive domains like healthcare, though it is incremental as it builds on prior work with a novel method for query selection.
The paper tackles the problem of opaque decision-making in machine learning by proposing a model that bases predictions on user-defined, interpretable binary queries, minimizing the expected number of queries needed for accurate prediction. Experiments on vision and NLP tasks show the approach's efficacy and superiority over post-hoc explanations.
There is a growing concern about typically opaque decision-making with high-performance machine learning algorithms. Providing an explanation of the reasoning process in domain-specific terms can be crucial for adoption in risk-sensitive domains such as healthcare. We argue that machine learning algorithms should be interpretable by design and that the language in which these interpretations are expressed should be domain- and task-dependent. Consequently, we base our model's prediction on a family of user-defined and task-specific binary functions of the data, each having a clear interpretation to the end-user. We then minimize the expected number of queries needed for accurate prediction on any given input. As the solution is generally intractable, following prior work, we choose the queries sequentially based on information gain. However, in contrast to previous work, we need not assume the queries are conditionally independent. Instead, we leverage a stochastic generative model (VAE) and an MCMC algorithm (Unadjusted Langevin) to select the most informative query about the input based on previous query-answers. This enables the online determination of a query chain of whatever depth is required to resolve prediction ambiguities. Finally, experiments on vision and NLP tasks demonstrate the efficacy of our approach and its superiority over post-hoc explanations.