论文标题
Gnnlens：一种视觉分析方法，用于预测图神经网络的误差诊断
GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks
论文作者
论文摘要
图形神经网络（GNN）旨在将深度学习技术扩展到图形数据，并在近年来在图形分析任务（例如节点分类）方面取得了重大进展。但是，类似于其他深层神经网络，例如卷积神经网络（CNN）和经常性神经网络（RNN），GNN的行为就像一个黑匣子，其细节隐藏在模型开发人员和用户中。因此，很难诊断出可能的GNN错误。尽管对CNN和RNN进行了许多视觉分析研究，但很少研究解决GNN的挑战。本文通过互动视觉分析工具Gnnlens填补了研究空白，以帮助模型开发人员和用户理解和分析GNN。具体而言，并行设置视图和投影视图使用户能够快速识别和验证错误预测集中的错误模式；图形视图和功能矩阵视图提供了单个节点的详细分析，以帮助用户形成有关错误模式的假设。由于GNN共同对图结构和节点特征进行建模，因此我们通过比较三种模型的预测来揭示两种类型的信息的相对影响：GNN，多层感知器（MLP）（MLP）和GNN而无需使用（GNNWUF）。两项案例研究和与领域专家的访谈表明，gnnlens在促进对GNN模型及其错误的理解方面的有效性。
Graph Neural Networks (GNNs) aim to extend deep learning techniques to graph data and have achieved significant progress in graph analysis tasks (e.g., node classification) in recent years. However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers and users. It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs. This paper fills the research gap with an interactive visual analysis tool, GNNLens, to assist model developers and users in understanding and analyzing GNNs. Specifically, Parallel Sets View and Projection View enable users to quickly identify and validate error patterns in the set of wrong predictions; Graph View and Feature Matrix View offer a detailed analysis of individual nodes to assist users in forming hypotheses about the error patterns. Since GNNs jointly model the graph structure and the node features, we reveal the relative influences of the two types of information by comparing the predictions of three models: GNN, Multi-Layer Perceptron (MLP), and GNN Without Using Features (GNNWUF). Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.
