mlsanityData to 13 Oct 2026

Empowering Counterfactual Reasoning over Graph Neural Networks through Inductivity

arXiv 2306.04835 ↗First posted 7 Jun 2023cs.LG cs.AI cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have various practical applications, such as drug discovery, recommendation engines, and chip design. However, GNNs lack transparency as they cannot provide understandable explanations for their predictions. To address this issue, counterfactual reasoning is used. The main goal is to make minimal changes to the input graph of a GNN in order to alter its prediction. While several algorithms have been proposed for counterfactual explanations of GNNs, most of them have two main drawbacks. Firstly, they only consider edge deletions as perturbations. Secondly, the counterfactual explanation models are transductive, meaning they do not generalize to unseen data. In this study, we introduce an inductive algorithm called INDUCE, which overcomes these limitations. By conducting extensive experiments on several datasets, we demonstrate that incorporating edge additions leads to better counterfactual results compared to the existing methods. Moreover, the inductive modeling approach allows INDUCE to directly predict counterfactual perturbations without requiring instance-specific training. This results in significant computational speed improvements compared to baseline methods and enables scalable counterfactual analysis for GNNs.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

23 of 35 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  2. 2017Graph Attention Networkscited by 8,888
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,467
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,422
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,135
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,003
  7. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 736
  8. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  9. 2020Parameterized Explainer for Graph Neural Networkcited by 425
  10. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  11. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  12. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
11 more
  1. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  2. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  3. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  4. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  5. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  6. 2020Chip Placement with Deep Reinforcement Learningcited by 83
  7. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  8. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  9. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  10. 2021Counterfactual Graphs for Explainable Classification of Brain Networkscited by 33
  11. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32

Built on by

Not cited yet.