I am Rongzhe Wei (魏容哲 in Chinese). I am a second year PhD in GCoM Group at Purdue University (will be transferred to ML Program in Georgia Tech 2023 Spring), supervised by Prof. Pan Li. Before joining GCoM group, I obtained my bachelor degree from the Honors Science Program (Mathematics - School of Mathematics and Statistics / Qian Xuesen College) at Xi'an Jiao Tong University in 2021. My research interests include:
- Machine learning theory on graphs
- Data privacy
- High dimensional statistics
This work tries to establish the connection between Bayesian inference over a graphical model and Graph neural networks. With such a connection, we are able to measure the values of nonlinear operations in GNNs for the node classification task. We obtain a “negative” result: When node attributes are not very... [Read More]
CIKM'22 "Self-supervision Meets Adversarial Perturbation A Novel Framework for Anomaly Detection"
with Yizhou Wang, Can Qin, Yi Xu, Yue Bai and Yun FuAnomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA2P, for unsupervised anomaly detection. After extracting representative embeddings from raw data, we apply random projections to the features and... [Read More]