mlsanityData to 7 Oct 2026

XInsight: Revealing Model Insights for GNNs with Flow-based Explanations

arXiv 2306.04791 ↗First posted 7 Jun 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Progress in graph neural networks has grown rapidly in recent years, with many new developments in drug discovery, medical diagnosis, and recommender systems. While this progress is significant, many networks are `black boxes' with little understanding of the `what' exactly the network is learning. Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models so that users can recognize errors and discover new knowledge. Therefore, the development of explainable AI algorithms is essential for us to reap the benefits of AI. We propose an explainability algorithm for GNNs called eXplainable Insight (XInsight) that generates a distribution of model explanations using GFlowNets. Since GFlowNets generate objects with probabilities proportional to a reward, XInsight can generate a diverse set of explanations, compared to previous methods that only learn the maximum reward sample. We demonstrate XInsight by generating explanations for GNNs trained on two graph classification tasks: classifying mutagenic compounds with the MUTAG dataset and classifying acyclic graphs with a synthetic dataset that we have open-sourced. We show the utility of XInsight's explanations by analyzing the generated compounds using QSAR modeling, and we find that XInsight generates compounds that cluster by lipophilicity, a known correlate of mutagenicity. Our results show that XInsight generates a distribution of explanations that uncovers the underlying relationships demonstrated by the model. They also highlight the importance of generating a diverse set of explanations, as it enables us to discover hidden relationships in the model and provides valuable guidance for further analysis.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 50 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

31 of 50 references.

References · 31

  1. 2017Graph Attention Networkscited by 8,854
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  9. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  12. 2019Graph Neural Networks for Social Recommendationcited by 711
19 more
  1. 2019Neural Graph Collaborative Filteringcited by 660
  2. 2020Directional Message Passing for Molecular Graphscited by 556
  3. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  4. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  5. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  6. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  7. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  8. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  9. 2020Self-supervised Graph Learning for Recommendationcited by 305
  10. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  11. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  12. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  13. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  14. 2022Biological Sequence Design with GFlowNetscited by 172
  15. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  16. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  17. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  18. 2021Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Drivingcited by 36
  19. 2019Deep Representation Learning for Social Network Analysiscited by 35

Built on by

Not cited yet.