Accumulated Local Effects and Graph Neural Networks for link prediction
By: Paulina Kaczyńska, Julian Sienkiewicz, Dominik Ślęzak
Potential Business Impact:
Shows how computer networks make decisions.
We investigate how Accumulated Local Effects (ALE), a model-agnostic explanation method, can be adapted to visualize the influence of node feature values in link prediction tasks using Graph Neural Networks (GNNs), specifically Graph Convolutional Networks and Graph Attention Networks. A key challenge addressed in this work is the complex interactions of nodes during message passing within GNN layers, complicating the direct application of ALE. Since a straightforward solution of modifying only one node at once substantially increases computation time, we propose an approximate method that mitigates this challenge. Our findings reveal that although the approximate method offers computational efficiency, the exact method yields more stable explanations, particularly when smaller data subsets are used. However, the explanations produced with the approximate method are not significantly different from the ones obtained with the exact method. Additionally, we analyze how varying parameters affect the accuracy of ALE estimation for both approaches.
Similar Papers
A Community-Enhanced Graph Representation Model for Link Prediction
Social and Information Networks
Finds hidden connections in online groups better.
Integrating Causal Inference with Graph Neural Networks for Alzheimer's Disease Analysis
Machine Learning (CS)
Finds brain parts that *cause* Alzheimer's.
Enhancing Explainability of Graph Neural Networks Through Conceptual and Structural Analyses and Their Extensions
Artificial Intelligence
Explains how computer graphs make decisions.