 |
Assistant Professor of Computer Science Email: ho.zhang@northeastern.edu |
Hi! I am an assistant professor of computer science at Northeastern University, Boston. I work on machine learning theory and methods, with a particular emphasis on the design and analysis of algorithms with better generalization, across heterogeneous tasks and diverse environments. I received my Ph.D. in computer science from Stanford. While studying at Stanford, I had the great fortune of working with members of the theoretical computer science group and the machine learning groups. Before moving to Boston, I was a postdoc at UPenn's statistics department for ten months. I received my B.Eng. from Shanghai Jiao Tong University. You can find complete information about me in my resume.
In my ongoing projects, my students and I have been developing algorithms with better generalization for modern machine learning. We are actively developing the principles and the empirical frameworks for multitask learning. This requires better modeling of task relationships and reconciling heterogeneous subpopulations. While we are driven by the technical questions, we are also striving for impact in social contexts; For instance, recently we've been looking to understand accidents on the road based on traffic network data.
Publications
Recent, Selected Papers
Identification of Negative Transfers in Multitask Learning Using Surrogate Models
Dongyue Li, Huy L. Nguyen, and H. R. Zhang
Transactions on Machine Learning Research (TMLR) 2023. Featured Certification
Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
Haotian Ju, Dongyue Li, Aneesh Sharma, and H. R. Zhang
Artificial Intelligence and Statistics (AISTATS) 2023
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
Haotian Ju, Dongyue Li, and H. R. Zhang
International Conference on Machine Learning (ICML) 2022
On the Generalization Effects of Linear Transformations in Data Augmentation
Sen Wu*, H. R. Zhang*, Gregory Valiant, and Christopher Ré
International Conference on Machine Learning (ICML) 2020
Understanding and Improving Information Transfer in Multi-Task Learning
Sen Wu*, H. R. Zhang*, and Christopher Ré
International Conference on Learning Representations (ICLR) 2020
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
Yuanzhi Li, Tengyu Ma, and H. R. Zhang*
Conference on Learning Theory (COLT) 2018. Best Paper Award
Approximate Personalized PageRank on Dynamic Graphs
H. R. Zhang, Peter Lofgren, and Ashish Goel
KDD 2016. Oral presentation
You can also see a more complete list of my publications, either chronologically, or categorized.
Here is my Google Scholar and DBLP profiles.
Here contains open-sourced experiment codes for the above projects on GitHub
Recent Activities
May 2023 (paper): Excited about a new paper at KDD! We provide a new method for multitask learning on graphs, with an application to supervised overlapping community detection.
April 2023 (funding): Grateful for Northeastern's TIER1 program for supporting our research on predicting road accidents using GNN.
March 2023 (paper): Excited about a newly accepted paper at TMLR! We present a new perspective to tackle the problem of negative transfer in multi-task learning.
March 2023 (talk): Visiting Yale and giving a guest lecture about “Generalization in Neural Networks: Recent Trend and Future Outlook.”
February 2023 (service): I'm orgazining an INFORMS session about “Recent Trend in Machine Learning Theory and Its Application to Operations Management.” If you are interested in giving a talk in this session, please send me an email.
February 2023 (talk): I gave a talk titled “Information Transfer in Multi-Task Learning, Data Augmentation, and Beyond” at AAAI.
A list of old updates
Research Lab/Teaching
Currently, I work with and advise the following list of students: Dongyue (Oliver) Li (Ph.D., starting 2021), Haotian Ju (MS in Data Analytics Engineering, 2022; Ph.D., starting 2023), Abhinav Nippani (MS in CS, since 2023), and Allen Ye (Undergraduate in CS, since 2023).
Here are the students whom have worked with me and whom have graduated from Northeastern, including their first employment: Virender Singh (MS in CS, 2021; First employment: Data Scientist at Salesforce), Minghao Liu (MS in CS, 2022; First employment, SDE at Palantir), and Shreya Singh (MS in CS, 2022).
Prospective students: We are always looking for students to join us. If you have ideas, I'd love to chat! You can take a look at my recent papers and recent projects at GitHub. We have a StatsML lab page if you are interested in learning more information. Undergraduate students interested in pursuing research are also encouraged to contact me. Students from underrepresented groups are especially encouraged to apply to our CS Ph.D. program and will be eligible for one year of fellowship. The ideal student needs to be self-motivated, and have a strong background in programming. If you are interested in working with my students and me as an RA, you can fill out this form, so that we are aware of your interest. We'll be in touch via email if we see a fit with our projects.
Here are the classes that I have been teaching at Northeastern:
CS 6140, Machine Learning, Fall 2023.
CS 7140, Advanced Machine Learning, Spring 2021, Spring 2022, Spring 2023.
DS 4400, Machine Learning and Data Mining I, Spring 2023.
DS 5220, Supervised Machine Learning and Learning Theory, Fall 2021, Fall 2022.
CS 7180, Special Topics in AI: Algorithmic and Statistical Aspects of Deep Learning, Fall 2020.
Education/Experience
2020: postdoc at UPenn (faculty host: Weijie J. Su).
2019: Ph.D. from Stanford (advisors: Ashish Goel and Greg Valiant).
2013: research assistant at Nanyang Technological University (advisor: Ning Chen, and also Xiaotie Deng).
2012: B.Eng. from Shanghai Jiao Tong University (advisors: Ning Chen and Pinyan Lu, part of the ACM class advised by Yong Yu).