Research

My research focuses on probabilistic models and neural networks for learning problems arising from real applications. My research topics include probabilistic modeling, generative models, biochemical data analysis, data-driven simulation of physics. Please see my publication list.

Research highlights

• Graph Generative Models

  1. The first rigorous probablistic treatment of autoregressive generative models for graphs
     Publications: [Chen et al., ICML 2021], [Han et al., JMLR 2023]

  2. Scaling up diffusion-based generative models to large graphs
     Publications: [Chen et al., ICML 2023]

• Machine Learning for Data-Driven Simulation of Fluid Dynamics

  1. Graph neural networks for simulation of fluid dynamics
     Publications: [Han et al., ICLR 2022]

  2. Modeling stochasticity in dynamic systems with generative models
     Publications: [Sun et al., Neurips 2023, Gao et al., CMAME]

• Machine Learning for Bioinformatics

  1. Matching molecules and mass spectra using neural methods
     Publications: [Zhu et al., MLCB], [Hosseini et al., Metabolites], [Li et al., Bioinformatics]

  2. Analyzing biochemical reactions and networks
     Publications: [Jiang et al., Bioinformatics], [Li et al., Bioinformatics], [Porokhin et al., Bioinformatics]

• Graph Learning and Applications

  1. Exploiting strong correlations among nearby data points and running inference within neighborhoods with a shared graph neural network
     Publications: [Liu et al., AISTATS 2019], [Liu et al., ACML 2020], [Appleby et al., AAAI 2020]

  2. Optimizing a neural network that predicts graph matchings and edit distances
     Publications: [Liu et al., ICML 2021], [Liu et al., TMLR 2022]

  3. Learned Graph Pruning for Enumerating Minimal Unsatisfiable Subsets (MUS)
     Publications: [Lymperopoulos et al., AISTATS 2024]

Advising

Current students

• Xu Han
• Jiajing Hu
• Yukun Li
• Panagiotis Lymperopoulos
• Xiaohui Chen

Former students

• Linfeng Liu, PhD (Research Scientist at Meta Research Boston)

Teaching

• Spring 2024: CS 135 Intro to Machine Learning
• Fall 2023: CS 137 Deep Neural Networks
• Spring 2023: CS 150 Deep Graph Learning
• Fall 2022: CS 137 Deep Neural Networks
• Fall 2021: CS 137 Deep Neural Networks
• Fall 2020: COMP 137 Deep Neural Networks
• Fall 2019: COMP 150 Machine Learning for Graph Analytics
• Spring 2019: COMP 150 Deep Neural Networks
• Fall 2018: COMP 135 Introduction to Machine Learning
• Spring 2018: COMP 135 Introduction to Machine Learning
• Fall 2017: COMP 150-01 Machine Learning for Ecology and Sustainability

Bio Sketch

I received my B.S. and M.S. in computer science respectively from Hebei University of Technology and Nanjing University LAMDA group. I completed my PhD at Oregon State University in 2016. My PhD advisor was Prof. Thomas Dietterich. Prior to joining Tufts, I worked as a postdoc researcher at Columbia University working with Prof. David Blei. Currently I am an assistant professor at the Computer Science Department of Tufts University.