TL;DR
The approach combines ideas from factual explainability with edge prediction models inspired by link prediction to enhance the quality, robustness, and interpretability of counterfactual explanations while keeping the method computationally tractable.
Counterfactual explanations for graph-structured data seek to determine minimal and realistic modifications required in an input graph to alter a model's prediction to a predefined output. Although counterfactual explainers that support modifying the graph by both adding and removing edges have recently emerged, there is still a lack of general and efficient methods, especially when considering the quality of the generated explanations. Moreover, the problem remains far from solved, as existing methods exhibit different strengths and weaknesses, often trading off between explanation size, coverage and quality. For this reason, it is important to identify where each method performs well and where it falls short, so as to guide future research in the field. Thus, our study compares six state-of-the-art (SOTA) models on a diverse set of real-world and synthetic datasets, covering both binary and multi-class graph and node classification tasks, and evaluates their performance using diverse quantitative and qualitative metrics.
This work proposes Graph Diffusion Counterfactual Explanation via Inversion (GDCE-I), a discrete denoising diffusion model with a novel discrete inversion scheme that enables distribution-aware edits leveraging the whole domain edit space and qualitatively shows that GDCE-I attains interpretable in-distribution solutions.
This study presents a graph-based explainable artificial intelligence framework for social network analysis, integrating graph neural models with SHAP (Shapley Additive Explanations) and other post-hoc explanation techniques. The framework is evaluated on the Stanford Network Analysis Project (SNAP) Facebook Dataset consisting of 15,000 nodes and 45,000 edges. Results from experiments show that the suggested model enhances classification performance by 7–12% compared to baseline methods while providing interpretable feature-level insights. The findings highlight the potential of combining graph learning with explainability to support transparent decision-making in network analysis tasks.
This work introduces XIGL, an architecture-agnostic human-in-the-loop strategy for removing shortcuts from GNNs, and develops an active learning strategy for prioritizing explanations that are more likely to display shortcut behavior, lowering annotation and cognitive costs.
A novel technique for post-hoc explainability queries in GNNs is introduced by focusing on the semifactual reasoning, and a novel learning architecture for addressing their computation is proposed.
Graph Neural Networks (GNNs) have become widely used for analyzing graph-structured data, motivating post-hoc explanation methods for interpreting pre-trained GNNs. However, most existing explainers have primarily been designed and evaluated in settings where the inference graph is structurally or distributionally similar to the graph used to train the GNN. This setting can be fragile in practical deployment, where inference time graphs may contain newly introduced nodes and edges that deviate substantially from the training distribution. Such Out-of-Distribution (OOD) entities can introduce spurious signals during explanation generation, causing explainers to highlight unreliable graph components. Nevertheless, the robustness of post-hoc GNN explainers under OOD-contaminated inference graphs remains largely unexplored. To address this gap, we propose ORExplainer (Out-of-Distribution Robust Explainer), a post-hoc node-level explanation framework for inference graphs containing OOD nodes. ORExplainer quantifies node-level distributional deviation using an energy-based score computed from a pre-trained GNN, and propagates this score to learn explanations that emphasize In-Distribution (ID) nodes while suppressing OOD influence. Experiments on synthetic and real-world datasets show that ORExplainer consistently provides more robust explanations across diverse node-level OOD settings, outperforming existing baselines. Our code is available at https://github.com/gunhee8178/ORExplainer.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
