GNNLens: A visual analytics approach for prediction error diagnosis of graph neural networks.

• Main Authors: JIN, Zhihua, WANG, Yong, WANG, Qianwen, MING, Yao, MA, Tengfei, QU, Huamin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Graph Neural Networks; Error Diagnosis; Visualization; Graphics and Human Computer Interfaces; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/7659; https://ink.library.smu.edu.sg/context/sis_research/article/8662/viewcontent/2011.11048.pdf
• Institution: Singapore Management University

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...