I am a graduant research assistant at School of Computing and Information (SCI), University of Pittsburgh. My major is Information Science and Technology. Currently, I work in PITT Computational Social Dynamics Lab (PICSO LAB) which is directed by Dr. Yu-Ru Lin. I am interested in machine learning, deep learning, data science and network science. With the escalating amount of heterogeneous, multi-sourced and time-varying datasets, I explore intelligent and computational methods to characterize underlying patterns, identify anomalous phenomena, and to forecast future’s evolutions. If you are interested in my research, please visit Research and Publication.
- 06/2020 Our paper StoCast: Stochastic Disease Forecasting with Progression Uncertainty is accepted by IEEE Journal of Biomedical and Health Informatics. We utilize deep generative learning to address the disease progression uncertainty in diease forecasting problem.
- 05/2019 2019 Summer Internship as Machine Learning SWE at Facebook (Menlo Park, CA).
- 03/2019 I pass my PhD comprehensive exam -- a milestone in my doctoral program.
- 07/2018 Our paper Deep into Hypersphere: Robust and Unsupervised Anomaly Detection in Dynamic Networks is accepted for inclusion in the IJCAI 2018. [Codes] [Slides]
- 06/2018 Received a GHC Student Scholarship to attend the 2018 Grace Hopper Celebration in Houston, Texas.
- 06/2018 Our CI-TM algorithm code is published now at github for the convenience of whom might need it. It is proposed in our paper Efficient collective influence maximization in cascading processes with first-order transitions.
- 05/2018 2018 Summer Internship at Samsung Research (Mountain View, CA).
- 08/2017 I received student travel grants from NSF & SIGWEB as well as SIGIR to attend CIKM 2017 in Singapore.
- 08/2017 Our paper Anomaly detection in dynamic networks using multi-view time-series hypersphere learning is accepted for inclusion in the CIKM 2017 conference. [Codes] [Slides].
- 03/2017 Our paper Efficient collective influence maximization in cascading processes with first-order transitions is published in Scientific Reports. We develop a new algorithm called "CI-TM" (codes available at github), which can quickly spot influential spreaders to promote information diffusion in networks.
- 10/2016 Our paper Collective Influence of Multiple Spreaders Evaluated by Tracing Real Information Flow in Large-Scale Social Networks is published in Scientific Reports.