XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks

06/05/2020
by   Thomas Schnake, et al.
0

Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explainable AI (XAI) approaches are not applicable. To a large extent, GNNs have remained black-boxes for the user so far. In this paper, we contribute by proposing a new XAI approach for GNNs. Our approach is derived from high-order Taylor expansions and is able to generate a decomposition of the GNN prediction as a collection of relevant walks on the input graph. We find that these high-order Taylor expansions can be equivalently (and more simply) computed using multiple backpropagation passes from the top layer of the GNN to the first layer. The explanation can then be further robustified and generalized by using layer-wise-relevance propagation (LRP) in place of the standard equations for gradient propagation. Our novel method which we denote as 'GNN-LRP' is tested on scale-free graphs, sentence parsing trees, molecular graphs, and pixel lattices representing images. In each case, it performs stably and accurately, and delivers interesting and novel application insights.

READ FULL TEXT
research
07/22/2022

Explaining Dynamic Graph Neural Networks via Relevance Back-propagation

Graph Neural Networks (GNNs) have shown remarkable effectiveness in capt...
research
07/25/2023

Transferability of Graph Neural Networks using Graphon and Sampling Theories

Graph neural networks (GNNs) have become powerful tools for processing g...
research
05/26/2022

DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

We propose the fully explainable Decision Tree Graph Neural Network (DT+...
research
04/18/2021

Ranking Structured Objects with Graph Neural Networks

Graph neural networks (GNNs) have been successfully applied in many stru...
research
06/20/2023

Hierarchical GNNs for Large Graph Generation

Large graphs are present in a variety of domains, including social netwo...
research
10/01/2020

Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking

Graph neural networks (GNNs) have become a popular approach to integrati...
research
01/25/2022

Unboxing the graph: Neural Relational Inference for Mobility Prediction

Predicting the supply and demand of transport systems is vital for effic...

Please sign up or login with your details

Forgot password? Click here to reset