Hongwei Jin

I am a Ph.D. candidate in computer science at University of Illinois at Chicago, under the supervision of Prof. Xinhua Zhang.

Contact: hjin25 (at) uic.edu, Github

Research

• Structured data representation

• Adversarial training

• Robustness certification on graph neural networks

• Convex / Non-convex optimization

• Neural network / deep learning

Conferences

• Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks
  Hongwei Jin, Zhan Shi, Ashish Peruri, Xinhua Zhang
  Advances in Neural Information Processing Systems (NeurIPS), 2020. [Spotlight, PDF, SlidesLive, code]

• Robust Training of Graph Convolutional Networks via Latent Perturbation
  Hongwei Jin, Xinhua Zhang
  European Conference on Machine Learning (ECML), 2020. [PDF, SlidesLive, code]

• Simulating Aggregation Algorithms for Empirical Verification of Resilient and Adaptive Federated Learning
  Hongwei Jin, Ning Yan, Masood Mortazavi
  IEEE/ACM International Conference on Big Data Computing, Applications and Technolgies (BDCAT), 2020. [PDF]

Workshops

• Latent Adversarial Training of Graph Convolutional Networks
  Hongwei Jin, Xinhua Zhang
  Learning and Reasoning with Graph-Structured Representations @ ICML, 2019. [PDF]

Tutorial / Notes

• Generative Models for Graphs, 2020

• Bayesian Optimization, 2018

• Variational Inference, 2018

• A Generic Approach for Escaping Saddle Points, 2018

• A Tutorial of AMPL for Linear Programming, 2014

Education

• 2015 - present, doctoral study in Computer Science at UIC, Chicago, IL

• 2012 - 2015, M.S. in Applied Mathematics at Illinois Institute of Technology, Chicago, IL

• 2008 - 2012, B.E. in Software Engineering at Northeastern University, China