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

Abstract

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.

arXiv commenteXplainable Artificial Intelligence. 1st World Conference on eXplainable Artificial Intelligence, xAI-2023, Lisbon, Portugal

References in corpus (16)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• Neural Message Passing for Quantum Chemistry
• Neural Graph Collaborative Filtering
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Self-supervised Graph Learning for Recommendation
• How to Explain Individual Classification Decisions
• Directional Message Passing for Molecular Graphs
• TUDataset: A collection of benchmark datasets for learning with graphs
• XGNN: Towards Model-Level Explanations of Graph Neural Networks
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Driving
• Molecular graph generation with Graph Neural Networks
• GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
• Graph Neural Networks for Social Recommendation
• VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation