Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· 0 citations· 1 references
TL;DR
Experiments on synthetic and real-world datasets show that ORExplainer consistently provides more robust explanations across diverse node-level OOD settings, outperforming existing baselines.
Abstract
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.
This survey provides a comprehensive overview of OOD detection methods, organizing them into traditional and deep learning families before examining graph-aware GNN-based approaches and synthesizing the conceptual relationships between these paradigms through three working hypotheses: graph-aware transfer, structure-sensitive scoring, and hybrid objective design.
Mao Nguyen, Thien Pham, Long Song Thien Nguyen et al.· IEEE Access· 0 citations
A novel Unified Counterfactual Explainer for GNNs that generates counterfactual explanations for both node and graph classification tasks through a unified approach, and offers maximum flexibility by supporting maximum flexibility.
This work proposes a novel Adaptive Dual-level Collaborative GNN associated with an adaptive dual-level collaborative mechanism, and shows that the ADC-GNN can inject the learned high-level information back into the node level, forming a closed-loop, bidirectional optimization process.
Graph Neural Networks (GNN) facilitate effective prediction on graph data such as molecules, media networks and neural network blueprints. GNNs facilitate prediction through message passing techniques which define how information flows from a node to its neighbors. Due to the ubiquity of the graph data type, the development of newer and better GNNs has garnered much interest in the machine learning community. However, GNN evaluation and benchmarking is primarily driven by classification tasks. Thus, prospective GNN message passing layers are evaluated on their ability to outperform prior work in classification contexts. In contrast, GNNs are equally capable of performing scalar regression prediction, yet this class of problem is often overlooked when proposing new GNNs while the best classification GNNs are utilized in an a priori or off-the-shelf manner for regression problems. In response, this paper studies the efficacy of GNN layers in a slew of regression contexts from rank ordering, error minimization and insight extraction. Results show that deep convolutional GNNs, particularly GEN, are more effective at these tasks than attention-based GNNs, while other classical, theoretically-inspired GNNs remain competitive and efficient.
Keith G. Mills, Aedan J. DeFrates, Joong Ho Kim· 0 citations
Graph Neural Networks (GNNs) are popular deep learning models designed to process graph-structured data through recursive neighborhood aggregations in the message passing process. When applied to semi-supervised node classification, the message-passing enables GNNs to understand short-range spatial interactions, but also causes them to suffer from over-smoothing and over-squashing. These challenges hinder model expressiveness and prevent the use of deeper models to capture long-range node interactions (LRIs) within the graph. Popular solutions for LRIs detection are either too expensive to process large graphs due to high time complexity or fail to generalize across diverse graph structures. To address these limitations, we propose a mechanism called information flow control, which leverages a novel connectivity measure, called information flow score, to address over-smoothing and over-squashing with linear computational overhead, supported by theoretical evidence. Building on this mechanism, we introduce DeltaGNN, to the best of our knowledge among the first scalable (featuring linear computational and memory complexity overhead) and generalizable (capable of effectively handling graphs with diverse homophily, density, and topology) architectures for long-range and short-range interaction detection. We benchmark our model across 10 real-world datasets, including graphs with varying sizes, topologies, densities, and homophilic ratios, showing superior performance with limited computational complexity.
Kevin Mancini, Islem Rekik· IEEE Transactions on Pattern...· 2 citations