Department of Computer and Information Sciences. Temple University.
Temple University, Philadelphia, PA 19122
I am a tenure-track Assistant Professor in Department of Computer and Information Sciences at Temple University. I am also a Visiting Research Collaborator in Department of Electrical and Computer Engineering at Princeton University. Before joining Temple University, I worked as a postdoctoral scholar, advised by H. Vincent Poor, in Department of Electrical and Computer Engineering at Princeton University. I received my Ph.D. in Statistics from Southern Methodist University advised by Hon Keung Tony Ng and Yulia R. Gel.
My research interests are graph mining, reliability theory, machine learning, (geometric) deep learning, nonparametric statistics, topological data analysis, semi-supervised classification, and life-testing procedures, in application to power systems and blockchain.
Recruiting New Students
I am looking for highly motivated and self-driven students, who are interested in machine learning/deep learning on graphs, data mining, and topological and geometric methods in statistics. Master’s and undergraduate students at Temple University are also welcome to apply. If you are interested, please contact me at email@example.com. Include your CV and brief highlights of ML/DL/Statistics-related projects.
|Mar 22, 2023||One paper was accepted to IEEE Transactions on Power Systems!|
|Mar 18, 2023||Our workshop Data Mining for Climate Change and Health Equity (DMC^2HE) was accepted by ICDM 2023!|
|Mar 6, 2023||Our workshop Bridge-AI: from Climate Change to Health Equity (BridgeAICCHE) was accepted by IJCAI 2023!|
|Feb 15, 2023||One paper was accepted to ICASSP 2023!|
NeurIPSTime Dimension Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series ForecastingIn Advances in Neural Information Processing Systems 2022
ECML-PKDDTopoAttn-Nets: Topological Attention in Graph Representation LearningIn European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2022
ICLRTAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series ForecastingIn International Conference on Learning Representations 2022
AAAIBScNets: Block Simplicial Complex Neural NetworksIn Proceedings of the AAAI Conference on Artificial Intelligence 2022
NeurIPSTopological Relational Learning on GraphsAdvances in Neural Information Processing Systems 2021