I am broadly interested in the machine learning field.
Currently, I am focusing on practical designs of machine learning algorithms in two exciting directions:
(i) building learning algorithms when only a limited amount of data is available.
(ii) building learning algorithms that can generalize to distributionally different tasks.
These areas span transfer learning, multi-task learning, contrastive learning, and data augmentation.
I am also interested in the generalization theory of deep learning and network analysis. My previous research focuses on model acceleration and system co-design.
Asterisk(*) indicates equal contribution
Optimal Intervention on Weighted Networks via Edge Centrality
Dongyue Li, Tina Eliassi-Rad, Hongyang R. Zhang
KDD Workshop on Epidemiology meets Data Mining and Knowledge discovery (epiDAMIK), 2022
Task Modeling: A Multitask Approach for Improving Robustness to Group Shifts
Dongyue Li, Huy L. Nguyen, Hongyang R. Zhang
ICML Workshop on Principles of Distribution Shift (PODS), 2022
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
Haotian Ju*, Dongyue Li*, Hongyang R. Zhang
Interntional Conference on Machine Learning (ICML), 2022
Also appears 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
Prior to my Ph.D. years
DTQAtten: Leveraging Dynamic Token-based Quantization for Efficient Attention Architecture
Tao Yang, Dongyue Li, Zhuoran Song, Yilong Zhao, Fangxin Liu, Zongwu Wang, Zhezhi He and Li Jiang
Conference on Design, Automation and Test in Europe (DATE), 2022
AdaptiveGCN: Efficient GCN Through Adaptively Sparsifying Graphs
Dongyue Li*, Tao Yang*, Lun Du, Zhezhi He, and Li Jiang
International Conference on Information and Knowledge Management (CIKM), 2021. Short paper.
Personalized and Environment-Aware Battery Prediction for Electric Vehicles
Dongyue Li*, Guangyu Li*, Bo Jiang*, Zhengping Che, and Yan Liu
KDD Workshop on Mining and Learning from Time Series (MiLeTS), 2021
PIMGCN: A ReRAM-based PIM Design for Graph Convolutional Network Acceleration
Tao Yang, Dongyue Li, Yibo Han, Yilong Zhao, Fangxin Liu, Xiaoyao Liang, Zhezhi He, and Li Jiang
Design Automation Conference (DAC), 2021
ReRAM-Sharing: Fine-Grained Weight Sharing for ReRAM-Based Deep Neural Network Accelerator
Dongyue Li*, Zhuoran Song*, Zhezhi He, Xiaoyao Liang, and Li Jiang
International Symposium on Circuits and Systems (ISCAS), 2021
Education & Work Experiences
Northeastern University, BOS, U.S.
Ph.D in Computer Science, Sep. 2021 to Present
Research Focus: Machine Learning Algorithms and Network Analysis
Advisors: Prof. Hongyang R. Zhang
Shanghai Jiao Tong University, SH, China
B.S. in Computer Science and Technology, Sep. 2016 to Jun. 2020 (Major)
Research Focus: Neural Network Acceleration Algorithm and Network Optimization
Advisors: Prof. Li Jiang
B.S. in Mathematics and Applied Mathematics, Mar. 2018 to Jun. 2020 (Minor)
Ralated Courses: Analysis, Abstracted Algebra, and Differential Equations
Shanghai Qi Zhi Institute, SH, China
Full-time Researcher, Aug. 2020 to Jun. 2021
Research Focus: Graph Neural Networks, Efficient Machine Learning, and System Co-design
Advisors: Prof. Li Jiang
DiDi Chuxing AI Labs, BJ, China
Research Intern, Jul. 2019 to Sep. 2019
Research Focus: Spatio-Temporal Data Mining
Advisors: Prof. Yan Liu
I like photographing, editing music, and watching stand-up comedy shows & movies for fun.
[My photographs in a microblog (Chinese Platform)]
I am a tennis fan. My favorite player is Simona Halep from Romania. She won the Wimbledon Champion of women's single 2019! I love playing tennis, swimming, and working out in the gym.