Jie Chen

Research Staff Member

Categories

Graph Deep Learning

Jie Chen received his B.S. degree in mathematics from Zhejiang University and Ph.D. degree in computer science from University of Minnesota. His research spans a broad spectrum of disciplines, including machine learning, statistics, scientific computing, and parallel computing. The results of his work have been published in prestigious journals and conferences in the respective fields. He was a recipient of SIAM Student Paper Prize in 2009, a plenary speaker at the 2017 International Conference on Preconditioning Techniques for Scientific and Industrial Applications, and a recipient of IBM Outstanding Technical Achievement Award in 2018. He has been PI and co-PI of projects supported by the U.S. Department of Energy.

Areas of Interest

  • Graph deep learning
  • Generative models
  • Structure learning
  • Stochastic optimization
  • Kernel methods
  • Gaussian processes
  • Parallel computing
  • Numerical linear algebra
  • Preconditioning
  • Multilinear algebra
  • Spectral graph theory

Top Work

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

Graph Deep Learning

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

AI in Finance

Scalable Graph Learning for Anti-Money Laundering: A First Look

Scalable Graph Learning for Anti-Money Laundering: A First Look

AI in Finance

Publications with the MIT-IBM Watson AI Lab

Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
 
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
 
Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
 
Online AI planning with graph neural networks and adaptive scheduling
Online AI planning with graph neural networks and adaptive scheduling
 
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
 
Embedding Compression with Isotropic Iterative Quantization
Embedding Compression with Isotropic Iterative Quantization
 
Scalable Graph Learning for Anti-Money Laundering: A First Look
Scalable Graph Learning for Anti-Money Laundering: A First Look
 
Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders