GRAPHSHAP: Motif-based Explanations for Black-box Graph Classifiers

by   Alan Perotti, et al.

Most methods for explaining black-box classifiers (e.g., on tabular data, images, or time series) rely on measuring the impact that the removal/perturbation of features has on the model output. This forces the explanation language to match the classifier features space. However, when dealing with graph data, in which the basic features correspond essentially to the adjacency information describing the graph structure (i.e., the edges), this matching between features space and explanation language might not be appropriate. In this regard, we argue that (i) a good explanation method for graph classification should be fully agnostic with respect to the internal representation used by the black-box; and (ii) a good explanation language for graph classification tasks should be represented by higher-order structures, such as motifs. The need to decouple the feature space (edges) from the explanation space (motifs) is thus a major challenge towards developing actionable explanations for graph classification tasks. In this paper we introduce GRAPHSHAP, a Shapley-based approach able to provide motif-based explanations for black-box graph classifiers, assuming no knowledge whatsoever about the model or its training data: the only requirement is that the black-box can be queried at will. Furthermore, we introduce additional auxiliary components such as a synthetic graph dataset generator, algorithms for subgraph mining and ranking, a custom graph convolutional layer, and a kernel to approximate the explanation scores while maintaining linear time complexity. Finally, we test GRAPHSHAP on a real-world brain-network dataset consisting of patients affected by Autism Spectrum Disorder and a control group. Our experiments highlight how the classification provided by a black-box model can be effectively explained by few connectomics patterns.


page 1

page 2

page 3

page 4


Explaining black-box text classifiers for disease-treatment information extraction

Deep neural networks and other intricate Artificial Intelligence (AI) mo...

Explanations for Monotonic Classifiers

In many classification tasks there is a requirement of monotonicity. Con...

EMAP: Explanation by Minimal Adversarial Perturbation

Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2...

Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Network

Deep neural networks (DNNs) can accurately decode task-related informati...

On the Limit of Explaining Black-box Temporal Graph Neural Networks

Temporal Graph Neural Network (TGNN) has been receiving a lot of attenti...

Compositional Explanations for Image Classifiers

Existing algorithms for explaining the output of image classifiers perfo...

Efficient Computation of Shap Explanation Scores for Neural Network Classifiers via Knowledge Compilation

The use of Shap scores has become widespread in Explainable AI. However,...

Please sign up or login with your details

Forgot password? Click here to reset