Shu Ding @ LAMDA, NJU-AI
|
丁 姝
|
|
Biography
Currently I am a Ph.D. candidate at the School of Artificial Intelligence in Nanjing University and a member of LAMDA Group(LAMDA Publications), led by professor Zhi-Hua Zhou.I received my B.Sc. degree in Information and Computing Science in June 2020 from Department of Mathematics, Nanjing University. In the same year, I was admitted to pursue for a M.Sc. degree in Nanjing University without entrance examination. I received my M.Sc. degree in Computer Technology in June 2023 from Department of Computer Science and Technology, Nanjing University.
Research Interests
My research interests broadly lie in Machine Learning and Data Mining, with a current focus on Federated Learning, Collaborative Learning, and Large Language Models (LLMs).
- With the growing prevalence of edge devices, massive amounts of data are naturally dispersed across numerous clients. Federated learning is a promising paradigm that enables model training by leveraging these distributed data while preserving privacy.
- Furthermore, I am also interested in the adaptation and application of Large Language Models, exploring how to efficiently fine-tune, personalize, and deploy these powerful foundation models in real-world scenarios to enhance their capability and reliability.
Publications
-
Towards Understanding the Dynamics of Low-Rank Adaptation.
Shu Ding, Yang Peng, Hangan Zhou, Xinyu Lu, Shangwei Chen, Junhua Huang, Mingxuan Yuan and Wei Wang.
In: Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, 2026.
-
Enhancing the performance of global model by improving the adaptability of local models in federated learning.
Wujun Zhou, Shu Ding, Zelin Li and Wei Wang.
In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025) , Montreal, Canada, 2025.
-
Collaborative Learning by Detecting Collaboration Partners.
Shu Ding and Wei Wang.
In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, Louisiana, 2022. (Spotlight)
Patents
- A method for identifying collaborative relationships among medical institutions for medical image processing. CN115714005A.
Teaching Assistant
- Introduction to Machine Learning Theory. (With Prof. Wei Wang; For Graduate Students, Spring, 2025)
- Neural Networks. (With Prof. Furao Shen and Baile Xu; For Undergraduate Students, Spring, 2024)
- Digital Image Processing. (With Prof. Wei Wang; For Undergraduate Students, Fall, 2021)
- LAMDA Machine Learning Summer Seminar. (For New Students in LAMDA, Summer, 2021)
Academic Service
Reviewer for Conferences: ICML, NeurIPS, ICLR, AAAI, etc.
Awards & Honors
Postgraduate Outstanding Graduate, Nanjing University, 2023.
Excellent Master Dissertation Award, Nanjing University, 2023.
Excellent Graduate Student, Nanjing University, 2022.
Tencent Scholarship, Nanjing University, 2022.
Academic Scholarship for Master Students, Nanjing University, 2020, 2021, 2022.
Outstanding Graduate, Nanjing University, 2020.
Training Plan of the National Basic Subject Top-notch Talent Scholarship, 2017, 2018, 2019, 2020.
People's Scholarship, Nanjing University, 2018, 2019.
Excellent Undergraduate Student Model, Nanjing University, 2018.
Excellent Undergraduate Student, Nanjing University, 2018.
Nanjing (H.K.) Association Elite Scholarship, Nanjing University, 2017.
Outstanding Freshman Scholarship, Nanjing University, 2016.
Correspondence
Email: dings@lamda.nju.edu.cn or dings@smail.nju.edu.cn
Office: Room 912, Computer Science Building, Xianlin Campus of Nanjing University
Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术国家重点实验室, 210023)