Can I trust you more? Model-Agnostic Hierarchical Explanations
This addresses the need for better interpretability in AI, particularly for understanding complex model behaviors, but it is incremental as it builds on existing explanation methods.
The paper tackles the problem of explaining complex dependencies like double negation in sentences and scene interactions in images captured by machine learning models, proposing Mahé to provide model-agnostic hierarchical explanations that distinguish between context-dependent and context-free interactions, with results showing improved local interaction interpretations over state-of-the-art methods.
Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mahé, a novel approach to provide Model-agnostic hierarchical éxplanations of how powerful machine learning models, such as deep neural networks, capture these interactions as either dependent on or free of the context of data instances. Specifically, Mahé provides context-dependent explanations by a novel local interpretation algorithm that effectively captures any-order interactions, and obtains context-free explanations through generalizing context-dependent interactions to explain global behaviors. Experimental results show that Mahé obtains improved local interaction interpretations over state-of-the-art methods and successfully explains interactions that are context-free.