# Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology

arXiv: https://arxiv.org/abs/2606.06224 · HTML: https://mlsanity.com/paper/2606.06224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [Explaining Explanations: Axiomatic Feature Interactions for Deep Networks](https://mlsanity.com/paper/2002.04138/) (2020)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [Building and Interpreting Deep Similarity Models](https://mlsanity.com/paper/2003.05431/) (2020)
- [Resolving challenges in deep learning-based analyses of histopathological images using explanation methods](https://mlsanity.com/paper/1908.06943/) (2019)
- [SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology](https://mlsanity.com/paper/2312.15010/) (2023)
- [The Clever Hans Effect in Unsupervised Learning](https://mlsanity.com/paper/2408.08041/) (2024)
- [ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification](https://mlsanity.com/paper/2108.10612/) (2021)
- [CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Models](https://mlsanity.com/paper/2501.05269/) (2025)
- [An Aggregation of Aggregation Methods in Computational Pathology](https://mlsanity.com/paper/2211.01256/) (2022)
- [xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology](https://mlsanity.com/paper/2406.04280/) (2024)
- [Model Agnostic Interpretability for Multiple Instance Learning](https://mlsanity.com/paper/2201.11701/) (2022)
- [Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks](https://mlsanity.com/paper/2304.05727/) (2023)
- [Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology](https://mlsanity.com/paper/2501.02922/) (2025)
- [Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features](https://mlsanity.com/paper/2408.17198/) (2024)
- [Multi-level Multiple Instance Learning with Transformer for Whole Slide Image Classification](https://mlsanity.com/paper/2306.05029/) (2023)
- [Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology](https://mlsanity.com/paper/2603.08328/) (2026)

## Abstract (arXiv)

Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that highlight influential regions but do not explain how evidence from different tissue regions is combined to produce a prediction. This limits interpretability, especially when decisions depend on interactions between tissue features. We introduce Symbolic explainable MIL (Symb-xMIL), a post-hoc explanation framework that quantifies how a MIL model's behavior aligns with human-readable decision rules, expressed as logical relationships (e.g., AND, OR, NOT) between input features. These alignment scores reveal semantic patterns underlying the model's predictions. We evaluate Symb-xMIL on synthetic and real-world histopathology datasets. On synthetic MIL data, Symb-xMIL reliably recovers ground-truth logical rules. In a clinical tumor detection task, the best-aligned rules uncover heterogeneous decision patterns and expose hidden model errors. On an HPV-prediction task on TCGA-HNSCC, a cohort of head and neck cancer, our framework refines patient survival stratification beyond HPV status with potential clinical relevance. Overall, Symb-xMIL extends MIL explainability beyond visual attribution toward structured, rule-based reasoning, enabling more transparent and semantically grounded interpretation of model predictions.