On May 10, the Hujiang Economics and Management Forum Series (106th Session) was held in the second conference room reporting hall on the fourth floor of Building A of the Management Building. Associate Researcher Zhou Lixin from the Information Management Department delivered an academic report titled ‘Research on Network Missing Node Detection Based on Self-supervised Learning.’
In his report, Zhou first discussed the importance of graph learning in network data mining. He proposed a self-supervised missing node detection model based on graph convolutional neural networks and introduced a missing node detection and verification model that incorporates contrastive learning methods. The model was applied to datasets in various fields, such as citation networks and social networks, and the results showed that the proposed model excelled in the task of missing node detection, demonstrating better performance and generalization capabilities compared to other methods.
Finally, Professor Zhang Huizhen and Lecturer Lu Zhi from the Information Management Department provided commentary on the lecture and engaged in an in-depth exchange and discussion with the teachers and students present. The attendees shared their views and questions about the content of the report, discussing the challenges and potential solutions that graph learning may encounter in practical applications.
Translated by Zhou Lixin
Reviewed by Fang Zhiming
