Model Agnostic Interpretability for Multiple Instance Learning

TL;DR

This paper introduces model-agnostic interpretability methods for Multiple Instance Learning, enhancing understanding of model decisions and improving interpretability accuracy by up to 30% across various datasets.

Contribution

It develops new model-agnostic interpretability approaches for MIL, addressing key interpretability requirements and demonstrating improved accuracy and scalability.

Findings

Interpretability accuracy increased by up to 30%

Methods effectively identify interactions between instances

Scalable to larger datasets for real-world applications

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.