mlsanityData to 14 Oct 2026

MEGAN: Multi-Explanation Graph Attention Network

arXiv 2211.13236 ↗First posted 23 Nov 2022cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications. This proves crucial to improve the interpretability of graph regression predictions, as explanations can be split into positive and negative evidence w.r.t to a reference value. Additionally, our attention-based network is fully differentiable and explanations can actively be trained in an explanation-supervised manner. We first validate our model on a synthetic graph regression dataset with known ground-truth explanations. Our network outperforms existing baseline explainability methods for the single- as well as the multi-explanation case, achieving near-perfect explanation accuracy during explanation supervision. Finally, we demonstrate our model's capabilities on multiple real-world datasets. We find that our model produces sparse high-fidelity explanations consistent with human intuition about those tasks.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

36 of 54 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  5. 2018Sanity Checks for Saliency Mapscited by 1,156
  6. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  7. 2021How Attentive are Graph Attention Networks?cited by 835
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  9. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  10. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  11. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  12. 2017The (Un)reliability of saliency methodscited by 333
24 more
  1. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  2. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 166
  3. 2020Drug discovery with explainable artificial intelligencecited by 118
  4. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  5. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  6. 2020Evaluating Explanations: How much do explanations from the teacher aid students?cited by 94
  7. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  8. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  9. 2017Exploring Human-like Attention Supervision in Visual Question Answeringcited by 36
  10. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
  11. 2021GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networkscited by 35
  12. 2021CYBORG: Blending Human Saliency Into the Loss Improves Deep Learningcited by 33
  13. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  14. 2021Supervising Model Attention with Human Explanations for Robust Natural Language Inferencecited by 29
  15. 2018Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistrycited by 25
  16. 2021Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsitycited by 20
  17. 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
  18. 2019Reliable and Explainable Machine Learning Methods for Accelerated Material Discoverycited by 18
  19. 2022Encoding Concepts in Graph Neural Networkscited by 18
  20. 2022BAGEL: A Benchmark for Assessing Graph Neural Network Explanationscited by 11
  21. 2020Scientific intuition inspired by machine learning generated hypothesescited by 7
  22. 2022DT+GNN: A Fully Explainable Graph Neural Network using Decision Treescited by 6
  23. 2022GRETEL: A unified framework for Graph Counterfactual Explanation Evaluationcited by 6
  24. 2022PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networkscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 1.

7 papers.

  1. 2024Global Concept Explanations for Graphs by Contrastive Learningcited by 2
  2. 2025Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scorescited by 2
  3. 2023Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studiescited by 1
  4. 2024Creating Healthy Friction: Determining Stakeholder Requirements of Job Recommendation Explanationscited by 1
  5. 2025Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantificationcited by 1
  6. 2025OKRA: an Explainable, Heterogeneous, Multi-Stakeholder Job Recommender Systemcited by 0
  7. 2026Concept Graph Convolutions: Message Passing in the Concept Spacecited by 0