Dongyue Li
(he/him/his)
PhD Student
Research interests
- Statistical machine learning
- Design and analysis of algorithms
- Artificial intelligence
- Data science
Education
- BS in Computer Science and Technology, Shanghai Jiao Tong University — China
Biography
Dongyue Li is a doctoral student at the Khoury College of Computer Sciences at Northeastern University, advised by Hongyang Zhang.
His doctoral work—which he began in 2021 and expects to complete in 2027—deals with machine learning. In particular, he is focusing on building learning algorithms that can generalize over tasks, as well as building algorithms under circumstances where available data is limited. These areas include multi-task learning, meta-learning, unsupervised and semi-supervised learning, data augmentation, and the theoretical properties of learning algorithms.
In addition to his doctoral research, Li is interested in learning theory (particularly deep learning theory) and social and information networks.
Recent publications
-
Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
Citation: Dongyue Li, Aneesh Sharma, Hongyang R. Zhang. (2024). Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity KDD, 1542-1553. https://doi.org/10.1145/3637528.3671835 -
Learning Tree-Structured Composition of Data Augmentation
Citation: Dongyue Li, Kailai Chen, Predrag Radivojac, Hongyang R. Zhang. (2024). Learning Tree-Structured Composition of Data Augmentation Trans. Mach. Learn. Res., 2024. https://openreview.net/forum?id=lmgf03HeqV