# Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology

arXiv: https://arxiv.org/abs/2206.01794 · HTML: https://mlsanity.com/paper/2206.01794/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 56 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Deep Learning for Identifying Metastatic Breast Cancer](https://mlsanity.com/paper/1606.05718/) (2016)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning](https://mlsanity.com/paper/1912.05743/) (2019)
- [Towards falsifiable interpretability research](https://mlsanity.com/paper/2010.12016/) (2020)
- [Deep learning-based survival prediction for multiple cancer types using histopathology images](https://mlsanity.com/paper/1912.07354/) (2019)
- [A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning](https://mlsanity.com/paper/2011.02679/) (2020)
- [Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset](https://mlsanity.com/paper/2010.08006/) (2020)
- [Resolving challenges in deep learning-based analyses of histopathological images using explanation methods](https://mlsanity.com/paper/1908.06943/) (2019)
- [Artificial Intelligence Assistance Significantly Improves Gleason Grading of Prostate Biopsies by Pathologists](https://mlsanity.com/paper/2002.04500/) (2020)
- [Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations](https://mlsanity.com/paper/2009.14001/) (2020)
- [Rethinking Machine Learning Model Evaluation in Pathology](https://mlsanity.com/paper/2204.05205/) (2022)

## Built on by (most cited first, 30 of 58)

- [Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images](https://mlsanity.com/paper/2306.07831/) (2023)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11643/) (2024)
- [Transcriptomics-guided Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11618/) (2024)
- [The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification](https://mlsanity.com/paper/2305.17891/) (2023)
- [SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology](https://mlsanity.com/paper/2312.15010/) (2023)
- [Inherently Interpretable Time Series Classification via Multiple Instance Learning](https://mlsanity.com/paper/2311.10049/) (2023)
- [PLUTO: Pathology-Universal Transformer](https://mlsanity.com/paper/2405.07905/) (2024)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology](https://mlsanity.com/paper/2406.04280/) (2024)
- [Learning biologically relevant features in a pathology foundation model using sparse autoencoders](https://mlsanity.com/paper/2407.10785/) (2024)
- [Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification](https://mlsanity.com/paper/2312.05490/) (2023)
- [Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis](https://mlsanity.com/paper/2410.14195/) (2024)
- [Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement](https://mlsanity.com/paper/2411.09894/) (2024)
- [Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2305.16912/) (2023)
- [Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology](https://mlsanity.com/paper/2501.02922/) (2025)
- [A self-supervised framework for learning whole slide representations](https://mlsanity.com/paper/2402.06188/) (2024)
- [From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification](https://mlsanity.com/paper/2408.09449/) (2024)
- [MergeUp-augmented Semi-Weakly Supervised Learning for WSI Classification](https://mlsanity.com/paper/2408.12825/) (2024)
- [Ordinal Multiple-instance Learning for Ulcerative Colitis Severity Estimation with Selective Aggregated Transformer](https://mlsanity.com/paper/2411.14750/) (2024)
- [Learning from Partial Label Proportions for Whole Slide Image Segmentation](https://mlsanity.com/paper/2405.09041/) (2024)
- [Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study](https://mlsanity.com/paper/2505.01109/) (2025)
- [SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology](https://mlsanity.com/paper/2303.13405/) (2023)
- [Detecting Domain Shift in Multiple Instance Learning for Digital Pathology Using Fr'echet Domain Distance](https://mlsanity.com/paper/2405.09934/) (2024)
- [PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization](https://mlsanity.com/paper/2503.06482/) (2025)
- [Mixed Models with Multiple Instance Learning](https://mlsanity.com/paper/2311.02455/) (2023)
- [Prototype-Based Multiple Instance Learning for Gigapixel Whole Slide Image Classification](https://mlsanity.com/paper/2503.08384/) (2025)
- [Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis](https://mlsanity.com/paper/2507.02395/) (2025)
- [Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning](https://mlsanity.com/paper/2509.04023/) (2025)
- [Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment](https://mlsanity.com/paper/2601.16027/) (2026)

## Abstract (arXiv)

Multiple Instance Learning (MIL) has been widely applied in pathology towards solving critical problems such as automating cancer diagnosis and grading, predicting patient prognosis, and therapy response. Deploying these models in a clinical setting requires careful inspection of these black boxes during development and deployment to identify failures and maintain physician trust. In this work, we propose a simple formulation of MIL models, which enables interpretability while maintaining similar predictive performance. Our Additive MIL models enable spatial credit assignment such that the contribution of each region in the image can be exactly computed and visualized. We show that our spatial credit assignment coincides with regions used by pathologists during diagnosis and improves upon classical attention heatmaps from attention MIL models. We show that any existing MIL model can be made additive with a simple change in function composition. We also show how these models can debug model failures, identify spurious features, and highlight class-wise regions of interest, enabling their use in high-stakes environments such as clinical decision-making.