mlsanityData to 14 Oct 2026

Estimating Subgraph Importance with Structural Prior Domain Knowledge

arXiv 2605.12009 ↗First posted 12 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture, and it does not require access to ground-truth target labels. Experiments on real-world graph datasets demonstrate that our method consistently outperforms existing baselines in subgraph importance estimation. Furthermore, we extend our method to identify important nodes within the graph.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

22 of 36 references.

References · 22

  1. 2018How Powerful are Graph Neural Networks?cited by 4,393
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  4. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  5. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  6. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  7. 2018Graph Convolutional Networks for Text Classificationcited by 345
  8. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  9. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 264
  10. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  11. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  12. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
10 more
  1. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  2. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  3. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  4. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  5. 2021User Preference-aware Fake News Detectioncited by 79
  6. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
  7. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  8. 2022Graph Neural Networks with Adaptive Readoutscited by 29
  9. 2021Blockchain Phishing Scam Detection via Multi-channel Graph Classificationcited by 4
  10. 2023Structural Explanations for Graph Neural Networks using HSICcited by 4

Built on by

Not cited yet.