Can I trust you more? Model-Agnostic Hierarchical Explanations

Michael Tsang, Youbang Sun, Dongxu Ren, Beibei Xin, Yan Liu

Abstract: 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 Explanations 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 provides explanations of interactions that are context-free.

Keywords: interpretability, interactions, context-dependent, context-free

TL;DR: A new framework for context-dependent and context-free explanations of predictions

Data: [SST](https://paperswithcode.com/dataset/sst), [WikiText-103](https://paperswithcode.com/dataset/wikitext-103), [WikiText-2](https://paperswithcode.com/dataset/wikitext-2)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/can-i-trust-you-more-model-agnostic/code)