Parallelizing Node-Level Explainability in Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) have demonstrated remarkable performance in a wide range of tasks, such as node classification, link prediction, and graph classification, by exploiting the structural information in graph-structured data. However, in node classification, computing node-level explainability becomes extremely time-consuming as the size of the graph increases, while batching strategies often degrade explanation quality. This paper introduces a novel approach to parallelizing node-level explainability in GNNs through graph partitioning. By decomposing the graph into disjoint subgraphs, we enable parallel computation of explainability for node neighbors, significantly improving the scalability and efficiency without affecting the correctness of the results, provided sufficient memory is available. For scenarios where memory is limited, we further propose a dropout-based reconstruction mechanism that offers a controllable trade-off between memory usage and explanation fidelity. Experimental results on real-world datasets demonstrate substantial speedups, enabling scalable and transparent explainability for large-scale GNN models.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 8 Jan 2026.
Builds on
31 of 39 references.
References · 31
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2018Sanity Checks for Saliency Mapscited by 1,149
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
- 2015Automatic differentiation in machine learning: a surveycited by 846
19 more
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
- 2021How Attentive are Graph Attention Networks?cited by 818
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
- 2019Graph Neural Networks for Social Recommendationcited by 711
- 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
- 2020Parameterized Explainer for Graph Neural Networkcited by 423
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
- 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
- 2022Graph neural networks for materials science and chemistrycited by 181
- 2019Explainability Techniques for Graph Convolutional Networkscited by 160
- 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
- 2020Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysiscited by 80
- 2021A Review of Graph Neural Networks and Their Applications in Power Systemscited by 62
- 2019Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Mapscited by 34
- 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 34
- 2021Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunitiescited by 22
- 2022Explainability in Graph Neural Networks: An Experimental Surveycited by 16
- 2023Evaluating Link Prediction Explanations for Graph Neural Networkscited by 2
- 2023Evaluating Neighbor Explainability for Graph Neural Networkscited by 1
Built on by
Not cited yet.