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

TL;DR

xAI-Drop introduces a explainability-driven regularizer for GNNs that enhances accuracy and interpretability by selectively excluding noisy network components during training.

Contribution

The paper presents xAI-Drop, a novel topological dropping regularizer that uses explainability to identify and exclude noisy elements in GNNs, improving performance and interpretability.

Findings

xAI-Drop outperforms existing dropping methods in accuracy.

xAI-Drop improves explanation quality of GNNs.

Empirical results on real-world datasets validate effectiveness.

Abstract

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.