Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks

2026-03-04

AI Summary

This work addresses the limited trustworthiness of Graph Neural Networks (GNNs) in high-stakes scenarios due to their poor interpretability. To this end, the authors propose XPlore, a method that jointly optimizes perturbations to both the adjacency matrix—supporting edge insertion and deletion—and node features within a unified gradient-based framework to generate richer and more realistic counterfactual explanations. Unlike existing approaches restricted to edge removal, XPlore overcomes this limitation and introduces a novel fidelity metric based on cosine similarity of graph embeddings. Extensive experiments across 13 real-world and 5 synthetic datasets demonstrate that XPlore achieves up to 56.3% higher effectiveness and 52.8% improved fidelity compared to state-of-the-art methods, all while maintaining computational efficiency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Graph Neural Networks (GNNs) are increasingly adopted across domains such as molecular biology and social network analysis, yet their black-box nature hinders interpretability and trust. This is especially problematic in high-stakes applications, such as predicting molecule toxicity, drug discovery, or guiding financial fraud detections, where transparent explanations are essential. Counterfactual explanations - minimal changes that flip a model's prediction - offer a transparent lens into GNNs' behavior. In this work, we introduce XPlore, a novel technique that significantly broadens the counterfactual search space. It consists of gradient-guided perturbations to adjacency and node feature matrices. Unlike most prior methods, which focus solely on edge deletions, our approach belongs to the growing class of techniques that optimize edge insertions and node-feature perturbations, here jointly performed under a unified gradient-based framework, enabling a richer and more nuanced exploration of counterfactuals. To quantify both structural and semantic fidelity, we introduce a cosine similarity metric for learned graph embeddings that addresses a key limitation of traditional distance-based metrics, and demonstrate that XPlore produces more coherent and minimal counterfactuals. Empirical results on 13 real-world and 5 synthetic benchmarks show up to +56.3% improvement in validity and +52.8% in fidelity over state-of-the-art baselines, while retaining competitive runtime.

Problem

• Graph Neural Networks
• Counterfactual Explanation
• Interpretability
• Edge Deletion
• Model Transparency

Innovation

• counterfactual explanation
• graph neural networks
• gradient-based perturbation
• edge insertion
• embedding fidelity