mlsanityData to 14 Oct 2026

GOAt: Explaining Graph Neural Networks via Graph Output Attribution

arXiv 2401.14578 ↗First posted 26 Jan 2024cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability. Most existing methods for explaining GNNs typically rely on training auxiliary models, resulting in the explanations remain black-boxed. This paper introduces Graph Output Attribution (GOAt), a novel method to attribute graph outputs to input graph features, creating GNN explanations that are faithful, discriminative, as well as stable across similar samples. By expanding the GNN as a sum of scalar products involving node features, edge features and activation patterns, we propose an efficient analytical method to compute contribution of each node or edge feature to each scalar product and aggregate the contributions from all scalar products in the expansion form to derive the importance of each node and edge. Through extensive experiments on synthetic and real-world data, we show that our method not only outperforms various state-ofthe-art GNN explainers in terms of the commonly used fidelity metric, but also exhibits stronger discriminability, and stability by a remarkable margin.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 26 Jan 2024.

Builds on

25 of 33 references.

References · 25

  1. 2017Inductive Representation Learning on Large Graphscited by 6,320
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  5. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  6. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  7. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  8. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  9. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  10. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  11. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 199
  12. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
13 more
  1. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  2. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  3. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  4. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  5. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  6. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  7. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  8. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  9. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  10. 2019Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagationcited by 29
  11. 2022Task-Agnostic Graph Explanationscited by 20
  12. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  13. 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2025From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Contextcited by 6
  2. 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Timecited by 5
  3. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  4. 2025Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstructioncited by 0
  5. 2025AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)cited by 0
  6. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  7. 2026FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networkscited by 0
  8. 2026Improving Adversarial Robustness of Attribution via Implicit Regularizationcited by 0
  9. 2026CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networkscited by 0
  10. 2026GraphSelect for Budgeted Representation Selection in Multimodal Graph Inferencecited by 0