# Model Agnostic Interpretability for Multiple Instance Learning

arXiv: https://arxiv.org/abs/2201.11701 · HTML: https://mlsanity.com/paper/2201.11701/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Multiple instance learning with graph neural networks](https://mlsanity.com/paper/1906.04881/) (2019)
- [Learning and Interpreting Multi-Multi-Instance Learning Networks](https://mlsanity.com/paper/1810.11514/) (2018)
- [Nested Multiple Instance Learning with Attention Mechanisms](https://mlsanity.com/paper/2111.00947/) (2021)

## Built on by (most cited first, 10 of 10)

- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [Inherently Interpretable Time Series Classification via Multiple Instance Learning](https://mlsanity.com/paper/2311.10049/) (2023)
- [xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology](https://mlsanity.com/paper/2406.04280/) (2024)
- [Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning](https://mlsanity.com/paper/2205.15367/) (2022)
- [Multiple Instance Verification](https://mlsanity.com/paper/2407.06544/) (2024)
- [Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology](https://mlsanity.com/paper/2603.08328/) (2026)
- [Scene-to-Patch Earth Observation: Multiple Instance Learning for Land Cover Classification](https://mlsanity.com/paper/2211.08247/) (2022)
- [Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property](https://mlsanity.com/paper/2405.14522/) (2024)
- [Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology](https://mlsanity.com/paper/2606.06224/) (2026)
- [CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning](https://mlsanity.com/paper/2609.08419/) (2026)

## Abstract (arXiv)

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.