Can I trust you more? Model-Agnostic Hierarchical ExplanationsDownload PDF

27 Sept 2018 (modified: 22 Oct 2023)ICLR 2019 Conference Blind SubmissionReaders: Everyone
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: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1812.04801/code)
13 Replies

Loading