mlsanityData to 7 Oct 2026

Factorized Explainer for Graph Neural Networks

arXiv 2312.05596 ↗First posted 9 Dec 2023cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. To open the black-box of these deep learning models, post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we show analytically that for a large class of explanation tasks, conventional approaches, which are based on the principle of graph information bottleneck (GIB), admit trivial solutions that do not align with the notion of explainability. Instead, we argue that a modified GIB principle may be used to avoid the aforementioned trivial solutions. We further introduce a novel factorized explanation model with theoretical performance guarantees. The modified GIB is used to analyze the structural properties of the proposed factorized explainer. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed factorized explainer.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 9 Dec 2023.

Builds on

24 of 33 references.

References · 24

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  5. 2021E(n) Equivariant Graph Neural Networkscited by 951
  6. 2018Link Prediction Based on Graph Neural Networkscited by 829
  7. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  9. 2019Graph Neural Networks for Social Recommendationcited by 711
  10. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  11. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  12. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
12 more
  1. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  2. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  3. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  4. 2020Graph Information Bottleneckcited by 168
  5. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  6. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  7. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  8. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  9. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  10. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  11. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  12. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 3.

8 papers.

  1. 2024TimeX++: Learning Time-Series Explanations with Information Bottleneckcited by 32
  2. 2024Protecting Your LLMs with Information Bottleneckcited by 26
  3. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  4. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  5. 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Timecited by 5
  6. 2024Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networkscited by 3
  7. 2025Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependenciescited by 1
  8. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0