Mengjia Xu
Mengjia Xu
Assistant Professor, Data Science
Guttenberg Information Technologies Center (GITC)
About Me
Dr. Mengjia Xu is currently an Assistant Professor at Department of Data Science, Ying Wu College of Computing, NJIT. She also holds a Research Affiliate position with the MIT NSF Center for Brains, Minds, and Machines (CBMM) at McGovern Institute for Brain Research. Prior to NJIT, she was a Research Assistant Professor in the Division of Applied Mathematics at Brown University. Concurrently, she held a joint postdoctoral position at MIT’s McGovern Institute for Brain Research. Before her joint postdoc at MIT and Brown, she completed her PhD degree at the Department of Computer Science, Northeastern University (China) and two-year joint PhD at Brown University.
Education
Ph.D.; Northeastern University; Computer Science; 2017
Website
2024 Spring Courses
DS 790A - DOCT DISSERTATION & RES
DS 725 - INDEPENDENT STUDY I
DS 677 - DEEP LEARNING
DS 700B - MASTER'S PROJECT
DS 792B - PRE-DOCTORAL RESEARCH
DS 726 - INDEPENDENT STUDY II
DS 701B - MASTER'S THESIS
DS 725 - INDEPENDENT STUDY I
DS 677 - DEEP LEARNING
DS 700B - MASTER'S PROJECT
DS 792B - PRE-DOCTORAL RESEARCH
DS 726 - INDEPENDENT STUDY II
DS 701B - MASTER'S THESIS
Past Courses
DS 675: MACHINE LEARNING
DS 677: DEEP LEARNING
DS 677: DEEP LEARNING
Research Interests
Machine learning theory; raph representation learning for diverse applications (e.g., Alzheimer's disease early stage detection, human brain aging trajectory detection, climate data modeling, etc.)
Journal Article
Xu, Mengjia, & Rangamani, Akshay, & Liao, Qianli, & Galanti, Tomer, & Poggio, Tomaso (2023). Dynamics in Deep Classifiers trained with the Square Loss: normalization, low rank, neural collapse and generalization bounds. Research,
Baker, Cole, & Su\'arez-M\'endez, Isabel, , & Smith, Grace, & Marsh, Elisabeth B, & Funke, Michael, & Mosher, John C, & Maest\'u, Fernando, , & Xu, Mengjia, & Pantazis, Dimitrios (2023). Hyperbolic graph embedding of MEG brain networks to study brain alterations in individuals with subjective cognitive decline. bioRxiv, 2023--10.
Varghese, Alan John, & Bora, Aniruddha, & Xu, Mengjia, & Karniadakis, George Em (2023). TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers. Neural Networks,
Xu, Mengjia, & Singh, Apoorva Vikram, & Karniadakis, George Em (2022). Dyng2g: An efficient stochastic graph embedding method for temporal graphs. IEEE Transactions on Neural Networks and Learning Systems,
Shukla, Khemraj, & Xu, Mengjia, & Trask, Nathaniel, & Karniadakis, George E (2022). Scalable algorithms for physics-informed neural and graph networks. Data-Centric Engineering, 3, e24.
Baker, Cole, & Su\'arez-M\'endez, Isabel, , & Smith, Grace, & Marsh, Elisabeth B, & Funke, Michael, & Mosher, John C, & Maest\'u, Fernando, , & Xu, Mengjia, & Pantazis, Dimitrios (2023). Hyperbolic graph embedding of MEG brain networks to study brain alterations in individuals with subjective cognitive decline. bioRxiv, 2023--10.
Varghese, Alan John, & Bora, Aniruddha, & Xu, Mengjia, & Karniadakis, George Em (2023). TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers. Neural Networks,
Xu, Mengjia, & Singh, Apoorva Vikram, & Karniadakis, George Em (2022). Dyng2g: An efficient stochastic graph embedding method for temporal graphs. IEEE Transactions on Neural Networks and Learning Systems,
Shukla, Khemraj, & Xu, Mengjia, & Trask, Nathaniel, & Karniadakis, George E (2022). Scalable algorithms for physics-informed neural and graph networks. Data-Centric Engineering, 3, e24.
SHOW MORE
Conference Proceeding
Norm-based Generalization Bounds for Sparse Neural Networks
2023
2023
Other
Generalization in deep network classifiers trained with the square loss
https://cbmm.mit.edu/sites/default/files/publications/TPR\_ver59.pdf, 2020
https://cbmm.mit.edu/sites/default/files/publications/TPR\_ver59.pdf, 2020