mlsanityData to 13 Oct 2026

PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes

arXiv 2208.03075 ↗First posted 5 Aug 2022cs.LGcited by 1

On the map: Knowledge distillation → Graph neural network distillation

Abstract (arXiv)

Graph Neural Networks (GNNs) are widely adopted in advanced AI systems due to their capability of representation learning on graph data. Even though GNN explanation is crucial to increase user trust in the systems, it is challenging due to the complexity of GNN execution. Lately, many works have been proposed to address some of the issues in GNN explanation. However, they lack generalization capability or suffer from computational burden when the size of graphs is enormous. To address these challenges, we propose a multi-level GNN explanation framework based on an observation that GNN is a multimodal learning process of multiple components in graph data. The complexity of the original problem is relaxed by breaking into multiple sub-parts represented as a hierarchical structure. The top-level explanation aims at specifying the contribution of each component to the model execution and predictions, while fine-grained levels focus on feature attribution and graph structure attribution analysis based on knowledge distillation. Student models are trained in standalone modes and are responsible for capturing different teacher behaviors, later used for particular component interpretation. Besides, we also aim for personalized explanations as the framework can generate different results based on user preferences. Finally, extensive experiments demonstrate the effectiveness and fidelity of our proposed approach.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation. Builds on 31 of its 45 references that are in the map. First posted on arXiv 5 Aug 2022.

Builds on

31 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021On Representation Knowledge Distillation for Graph Neural Networks9 Nov
  2. 2021Graph-Free Knowledge Distillation for Graph Neural Networks16 May

Other references · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,180
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,515
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,055
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,911
  6. 2020Knowledge Distillation: A Surveycited by 1,590
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,544
  8. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,203
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,135
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 736
  11. 2019Neural Graph Collaborative Filteringcited by 660
  12. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
17 more
  1. 2020Parameterized Explainer for Graph Neural Networkcited by 425
  2. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  3. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  4. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  5. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  6. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  7. 2021Does Knowledge Distillation Really Work?cited by 188
  8. 2018Knowledge Distillation by On-the-Fly Native Ensemblecited by 186
  9. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  10. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 81
  11. 2017Detecting Statistical Interactions from Neural Network Weightscited by 80
  12. 2020How does this interaction affect me? Interpretable attribution for feature interactionscited by 73
  13. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
  14. 2019Spam Review Detection with Graph Convolutional Networkscited by 57
  15. 2020GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detectioncited by 54
  16. 2019Sharing Attention Weights for Fast Transformercited by 34
  17. 2021Learning Interpretation with Explainable Knowledge Distillationcited by 13

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022INGREX: An Interactive Explanation Framework for Graph Neural Networkscited by 0