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.

Ph.D. ; Northeastern University ; Computer Science ; 2017

https://gracexu182.github.io/

DS 790A - DOCT DISSERTATION & RES

DS 701C - MASTER'S THESIS

DS 683 - GRAPH NEURAL NETWORKS

DS 725 - INDEPENDENT STUDY I

DS 700B - MASTER'S PROJECT

DS 792B - PRE-DOCTORAL RESEARCH

DS 726 - INDEPENDENT STUDY II

DS 488 - INDEPENDENT STUDY IN DS

DS 701B - MASTER'S THESIS

Machine learning theory; graph representation learning for diverse applications (e.g., Alzheimer's disease early stage detection, human brain aging trajectory detection, climate data modeling, etc.)

Mengjia Xu, Akshay Rangamani, Qianli Liao, Tomer Galanti, Tomaso Poggio. 2023. "Dynamics in Deep Classifiers trained with the Square Loss: normalization, low rank, neural collapse and generalization bounds." Research .

Cole Baker, Su\'arez-M\'endez, Isabel, Grace Smith, Elisabeth B Marsh, Michael Funke, John C Mosher, Maest\'u, Fernando, Mengjia Xu, Dimitrios Pantazis. 2023. "Hyperbolic graph embedding of MEG brain networks to study brain alterations in individuals with subjective cognitive decline." bioRxiv , pp. 2023--10.

Alan John Varghese, Aniruddha Bora, Mengjia Xu, George Em Karniadakis. 2023. "TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers." Neural Networks .

Mengjia Xu, Apoorva Vikram Singh, George Em Karniadakis. 2022. "Dyng2g: An efficient stochastic graph embedding method for temporal graphs." IEEE Transactions on Neural Networks and Learning Systems .

Khemraj Shukla, Mengjia Xu, Nathaniel Trask, George E Karniadakis. 2022. "Scalable algorithms for physics-informed neural and graph networks." Data-Centric Engineering , vol. 3 , pp. e24.

"Norm-based Generalization Bounds for Sparse Neural Networks"
2023.

"Generalization in deep network classifiers trained with the square loss"
https://cbmm.mit.edu/sites/default/files/publications/TPR\_ver59.pdf, 2020.