# Global explainability of a deep abstaining classifier

arXiv: https://arxiv.org/abs/2504.01202 · HTML: https://mlsanity.com/paper/2504.01202/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## 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)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Combating Label Noise in Deep Learning Using Abstention](https://mlsanity.com/paper/1905.10964/) (2019)
- [Extraction of Salient Sentences from Labelled Documents](https://mlsanity.com/paper/1412.6815/) (2014)
- [Topological Interpretability for Deep-Learning](https://mlsanity.com/paper/2305.08642/) (2023)
- [Why I'm not Answering: Understanding Determinants of Classification of an Abstaining Classifier for Cancer Pathology Reports](https://mlsanity.com/paper/2009.05094/) (2020)

## Abstract (arXiv)

We present a global explainability method to characterize sources of errors in the histology prediction task of our real-world multitask convolutional neural network (MTCNN)-based deep abstaining classifier (DAC), for automated annotation of cancer pathology reports from NCI-SEER registries. Our classifier was trained and evaluated on 1.04 million hand-annotated samples and makes simultaneous predictions of cancer site, subsite, histology, laterality, and behavior for each report. The DAC framework enables the model to abstain on ambiguous reports and/or confusing classes to achieve a target accuracy on the retained (non-abstained) samples, but at the cost of decreased coverage. Requiring 97% accuracy on the histology task caused our model to retain only 22% of all samples, mostly the less ambiguous and common classes. Local explainability with the GradInp technique provided a computationally efficient way of obtaining contextual reasoning for thousands of individual predictions. Our method, involving dimensionality reduction of approximately 13000 aggregated local explanations, enabled global identification of sources of errors as hierarchical complexity among classes, label noise, insufficient information, and conflicting evidence. This suggests several strategies such as exclusion criteria, focused annotation, and reduced penalties for errors involving hierarchically related classes to iteratively improve our DAC in this complex real-world implementation.