Work

Accumulated local effects and graph neural networks for link prediction

Year: 2026

Type: article

Abstract: 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 among nodes during message passing within GNN layers, which complicate the direct application of ALE. Since a straightforward solution of modifying only one node at a time substantially increases computation time, we propose an approximate method that mitigates this issue. 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 by the approximate method are not significantly different from those obtained by the exact method. Additionally, we analyze how varying parameters affect the accuracy of ALE estimation for both approaches.

Source: Scientific Reports

DOI: 10.1038/s41598-026-39000-w

Authors: Paulina Kaczyńska, Julian Sienkiewicz, Dominik Ślęzak

Institutions: Institute of Fundamental Technological Research, University of Warsaw, Polish Academy of Sciences, Warsaw University of Technology

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,690

Funders: European Commission, Politechnika Warszawska, HORIZON EUROPE Framework Programme, Research Executive Agency