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

TL;DR

This paper introduces IFEXPLAINER, a novel method for explaining GNN predictions in digital pathology by measuring information flow to identify necessary and sufficient substructures, improving interpretability in clinical decisions.

Contribution

The paper proposes a new explanation framework for GNNs that uses directional information flow and introduces $f$-information to generate necessary and sufficient explanations.

Findings

IFEXPLAINER outperforms existing explainers on breast cancer subtyping.

The method effectively identifies crucial biological substructures.

Experimental results demonstrate improved interpretability and accuracy.

Abstract

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.