mlsanityData to 14 Oct 2026

Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows

arXiv 2112.09895 ↗First posted 18 Dec 2021cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

As Graph Neural Networks (GNNs) are widely adopted in digital pathology, there is increasing attention to developing explanation models (explainers) of GNNs for improved transparency in clinical decisions. Existing explainers discover an explanatory subgraph relevant to the prediction. However, such a subgraph is insufficient to reveal all the critical biological substructures for the prediction because the prediction will remain unchanged after removing that subgraph. Hence, an explanatory subgraph should be not only necessary for prediction, but also sufficient to uncover the most predictive regions for the explanation. Such explanation requires a measurement of information transferred from different input subgraphs to the predictive output, which we define as information flow. In this work, we address these key challenges and propose IFEXPLAINER, which generates a necessary and sufficient explanation for GNNs. To evaluate the information flow within GNN's prediction, we first propose a novel notion of predictiveness, named f-information, which is directional and incorporates the realistic capacity of the GNN model. Based on it, IFEXPLAINER generates the explanatory subgraph with maximal information flow to the prediction. Meanwhile, it minimizes the information flow from the input to the predictive result after removing the explanation. Thus, the produced explanation is necessarily important to the prediction and sufficient to reveal the most crucial substructures. We evaluate IFEXPLAINER to interpret GNN's predictions on breast cancer subtyping. Experimental results on the BRACS dataset show the superior performance of the proposed method.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 18 Dec 2021.

Builds on

30 of 41 references.

References · 30

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  4. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  5. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  6. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 388
  7. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  8. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  9. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  10. 2020A Theory of Usable Information Under Computational Constraintscited by 162
  11. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  12. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
18 more
  1. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  2. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  3. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  4. 2019CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Imagescited by 57
  5. 2021A Survey on Graph-Based Deep Learning for Computational Histopathologycited by 41
  6. 2017Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classificationcited by 40
  7. 2020Representation Learning of Histopathology Images using Graph Neural Networkscited by 40
  8. 2020Quantifying Explainers of Graph Neural Networks in Computational Pathologycited by 35
  9. 2020HACT-Net: A Hierarchical Cell-to-Tissue Graph Neural Network for Histopathological Image Classificationcited by 33
  10. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  11. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  12. 2021Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphscited by 22
  13. 2019Histographs: Graphs in Histopathologycited by 20
  14. 2021HistoCartography: A Toolkit for Graph Analytics in Digital Pathologycited by 20
  15. 2019Weakly Supervised Prostate TMA Classification via Graph Convolutional Networkscited by 17
  16. 2020Towards Explainable Graph Representations in Digital Pathologycited by 17
  17. 2020Visualization for Histopathology Images using Graph Convolutional Neural Networkscited by 12
  18. 2018Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profilescited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  2. 2023A Survey on Explainability of Graph Neural Networkscited by 29
  3. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  4. 2024Graph Neural Networks in Histopathology: Emerging Trends and Future Directionscited by 13