李 岚 Lan Li (Lan. L) Ph.D. Student, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Email: lil [at] lamda.nju.edu.cn Github: https://github.com/Lain810 Laboratory: Shaoyifu Building, Xianlin Campus of Nanjing University

Biography

I received my B.Sc. degree from UESTC(University of Electronic Science and Technology of China) in June 2019. In the same year, I was admitted to study for a M.Sc. degree in Nanjing University without entrance examination.

I received my M.Sc. degree in School of Artificial Intelligence from Nanjing University in June 2022. In the same year, I was admitted to study for a Ph.D. degree in School of Artificial Intelligence from Nanjing University, which is also in the LAMDA Group led by Prof. Zhi-Hua Zhou., under the supervision of Prof. De-Chuan Zhan and Han-Jia Ye.

Research Interests

Lan mainly focuses on machine learning, especially:

Class-imbalanced Learning

• Class-imbalanced learning focuses on addressing the challenge of datasets with imbalanced class distributions, where one or more classes have significantly fewer instances compared to others. This problem is common in many real-world applications, such as medical diagnosis, fraud detection, and text classification.

Semi-Supervised Learning

• Semi-supervised learning is a broad category of machine learning that uses labeled data to ground predictions, and unlabeled data to learn the shape of the larger data distribution. Practitioners can achieve strong results with fractions of the labeled data, and as a result, can save valuable time and money.

Federated Learning

• Federated learning is a decentralized learning approach that enables training machine learning models on distributed data sources while keeping the data local and preserving privacy.

Publications - Conference & Journal

Lan Li, Xin-Chun Li, De-chuan Zhan, Han-Jia Ye. Enhancing Class-Imbalanced Learning with Pre-trained Guidance through Class-Conditional Knowledge Distillation. (ICML-24)

Lan Li, Bo-wen Tao, Lu Han, De-chuan Zhan, Han-Jia Ye. Twice Class Bias Correction for Imbalanced Semi-Supervised Learning. In 38th AAAI Conference on Artificial Intelligence (AAAI-24) [Paper]

Lan Li, De-Chuan Zhan, Xin-Chun Li . Aligning Model Outputs for Class Imbalanced Non-IID Federated Learning. In: Machine Learning. [paper]

Bowen Tao, Lan Li, Xin-Chun Li, De-Chuan Zhan. CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-24) [paper]

Xin-Chun Li, Jin-Lin Tang, Bo Zhang, Lan Li, De-Chuan Zhan. Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks. In: Advances in Neural Information Processing Systems 37 (NeurIPS'24) [paper]

Manuscripts

Xin-Chun Li , Lan Li, De-Chuan Zhan, Yunfeng Shao, Bingshuai Li, Shaoming Song. Preliminary Steps Towards Federated Sentiment Classification. CoRR 2021. [paper]

Selected Awards & Honors

• China Mobile Corporate Scholarship, 2024 (移动之光·数智创新奖学金)
• HUAWEI Fellowship for Outstanding Contribution, 2023 (华为-南京大学联合实验室优秀学生奖)
• Bank of Jiangsu Scholarship scholarship, 2023 (江苏银行奖学金)
• Excellent graduate student from Nanjing University, 2022 2023 (南京大学优秀研究生)
• Fuyou Scholarship, 2019 (福佑奖学金)
• Outstanding Graduate of Sichuan Province. 2019 (四川省优秀毕业生)
• Outstanding Graduate of UESTC. 2019 (电子科技大学优秀毕业生)
• Outstanding Winner in MCM/ICM. 2018 (美国大学生数学建模竞赛特等奖)
• Wu-Liang-Ye Scholarship(Enterprise Scholarship). 2018 (五粮液奖学金)
• National Undergraduate Scholarship. 2017 (国家奖学金)

Projects

• 数据分布不满足独立同分布条件下的分布式模型重用技术I期 (2019-2021, 华为-南京大学联合实验室)
• 数据分布不满足独立同分布条件下的分布式模型重用技术II期 (2019-2022, 华为-南京大学联合实验室)
• 科技创新2030-‘新一代人工智能’重大项目--智能医生助理关键技术及应用研究 (2020-2023)
• 江苏省研究生科研创新计划 (2024-2025)

Teaching Assistant

• 2020年秋季 高级机器学习 (本研共修; 詹德川教授)

• 2022年秋季 高级机器学习 (本研共修; 詹德川教授)

• 2024年春季 高级机器学习 (本研共修; 詹德川教授)

• 2024年春季 智能系统设计与应用 (研究生课程; 詹德川教授)

Correspondence

Email: lil [at] lamda.nju.edu.cn, mrlilan [at] foxmail.com
Office: Room A201, Shaoyifu Building, Xianlin Campus of Nanjing University
Address: Lan Li, 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.)