Dongyue (Oliver) Li

I am a Ph.D. Student in the Khoury College of Computer Sciences at Northeastern University starting from Fall 2021. I am fortunate to work with Professor Hongyang R. Zhang.

My current research interest lies in: (i) designing robust multitask learning systems that effectively combat negative transfers and data heterogeneity; (ii) improving generalization capabilities of modern machine learning models, such as learning from limited labeled data or noisy data; (iii) analyzing and learning from network data. I am excited to develop principled approaches to these related problems in multitask learning, transfer learning, and self-supervised learning.

I obtained my bachelor's degree in Computer Science from Shanghai Jiao Tong University and minored in Mathematics and Applied Mathematics.

Email  /  CV  /  Github

• Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
  Dongyue Li, Haotian Ju, Aneesh Sharma, Hongyang R. Zhang
  SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
  [Code]

• Identification of Negative Transfers in Multitask Learning Using Surrogate Models
  Dongyue Li, Huy L. Nguyen, Hongyang R. Zhang
  Transactions on Machine Learning Research (TMLR), 2023 (Featured Certification)
  [Code] [Presented in NeurIPS Workshop on Distribution Shifts (DistShift), 2022]

• Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
  Haotian Ju, Dongyue Li, Aneesh Sharma, Hongyang R. Zhang
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
  [Code]

• Optimal Intervention on Weighted Networks via Edge Centrality
  Dongyue Li, Tina Eliassi-Rad, Hongyang R. Zhang
  SIAM International Conference on Data Mining (SDM), 2023
  [Code] [Presented in KDD Workshop on Epidemiology meets Data Mining and Knowledge Discovery (epiDAMIK), 2022]

• Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
  Haotian Ju*, Dongyue Li*, Hongyang R. Zhang
  International Conference on Machine Learning (ICML), 2022
  [Code] [Presented in ICML Workshop on Updatable Machine Learning (UpML), 2022]

• Improved Regularization and Robustness for Fine-tuning in Neural Networks
  Dongyue Li, Hongyang R. Zhang
  Advances in Neural Information Processing Systems (NeurIPS), 2021
  [Code]

Asterisk(*) indicates equal contribution

Teaching Assistant
CS 7140: Adavanced Machine Learning, Northeastern University, Spring 2023
Instructor: Professor Hongyang R. Zhang

Full-time Researcher
Shanghai Qi Zhi Institute, Shanghai, Aug. 2020 to Jun. 2021
Research Focus: Graph Neural Networks, Efficient Machine Learning, and System Co-design
Advisors: Professor Li Jiang

Research Intern
DiDi Chuxing AI Labs, Beijing, Jul. 2019 to Sep. 2019
Research Focus: Spatio-Temporal Data Mining
Advisors: Professor Yan Liu

Credit to this webpage template