xAI-Drop: Don't Use What You Cannot Explain

Graph Neural Networks (GNNs) have emerged as the predominant paradigm for learning from graph-structured data, offering a wide range of applications from social network analysis to bioinformatics. Despite their versatility, GNNs face challenges such as lack of generalization and poor interpretabilit...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Marco De Luca, Vincenzo, Longa, Antonio, Passerini, Andrea, Liò, Pietro
Format: Article
Language:English
Subjects:
Bioinformatics
Graph neural networks
Identification methods
Network analysis
Robustness
Social networks
State-of-the-art reviews
Structured data
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Graph Neural Networks (GNNs) have emerged as the predominant paradigm for learning from graph-structured data, offering a wide range of applications from social network analysis to bioinformatics. Despite their versatility, GNNs face challenges such as lack of generalization and poor interpretability, which hinder their wider adoption and reliability in critical applications. Dropping has emerged as an effective paradigm for improving the generalization capabilities of GNNs. However, existing approaches often rely on random or heuristic-based selection criteria, lacking a principled method to identify and exclude nodes that contribute to noise and over-complexity in the model. In this work, we argue that explainability should be a key indicator of a model's quality throughout its training phase. To this end, we introduce xAI-Drop, a novel topological-level dropping regularizer that leverages explainability to pinpoint noisy network elements to be excluded from the GNN propagation mechanism. An empirical evaluation on diverse real-world datasets demonstrates that our method outperforms current state-of-the-art dropping approaches in accuracy, and improves explanation quality.
ISSN:2331-8422