mlsanityData to 14 Oct 2026

Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation

arXiv 2103.13944 ↗First posted 25 Mar 2021cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Prior works on formalizing explanations of a graph neural network (GNN) focus on a single use case - to preserve the prediction results through identifying important edges and nodes. In this paper, we develop a multi-purpose interpretation framework by acquiring a mask that indicates topology perturbations of the input graphs. We pack the framework into an interactive visualization system (GNNViz) which can fulfill multiple purposes: Preserve,Promote, or Attack GNN's predictions. We illustrate our approach's novelty and effectiveness with three case studies: First, GNNViz can assist non expert users to easily explore the relationship between graph topology and GNN's decision (Preserve), or to manipulate the prediction (Promote or Attack) for an image classification task on MS-COCO; Second, on the Pokec social network dataset, our framework can uncover unfairness and demographic biases; Lastly, it compares with state-of-the-art GNN explainer baseline on a synthetic dataset.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

39 of 50 references.

References · 39

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  11. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
27 more
  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  4. 2018Sanity Checks for Saliency Mapscited by 1,156
  5. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  6. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  7. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  8. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  9. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  10. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  11. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  12. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  13. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
  14. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  15. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 345
  16. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
  17. 2018Adversarial Attack on Graph Structured Datacited by 301
  18. 2018Deep Face Recognition: A Surveycited by 276
  19. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  20. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  21. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 255
  22. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  23. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  24. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  25. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  26. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  27. 2019AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinatescited by 24

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  2. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  3. 2023Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapescited by 1