Model Agnostic Interpretability for Multiple Instance Learning
Abstract
In Multiple Instance Learning (MIL), models are trained using bags of instances, where only a single label is provided for each bag. A bag label is often only determined by a handful of key instances within a bag, making it difficult to interpret what information a classifier is using to make decisions. In this work, we establish the key requirements for interpreting MIL models. We then go on to develop several model-agnostic approaches that meet these requirements. Our methods are compared against existing inherently interpretable MIL models on several datasets, and achieve an increase in interpretability accuracy of up to 30%. We also examine the ability of the methods to identify interactions between instances and scale to larger datasets, improving their applicability to real-world problems.
Cite
@article{arxiv.2201.11701,
title = {Model Agnostic Interpretability for Multiple Instance Learning},
author = {Joseph Early and Christine Evers and Sarvapali Ramchurn},
journal= {arXiv preprint arXiv:2201.11701},
year = {2022}
}
Comments
25 pages (9 content, 2 acknowledgement + references, 14 appendix). 16 figures (3 main content, 13 appendix). Submitted and accepted to ICLR 22, see http://openreview.net/forum?id=KSSfF5lMIAg Revisions: v2) Added additional acknowledgements v3) Updated to ICLR camera ready version