Tingji Huang @ LAMDA

黄廷基
Tingji Huang
M.Sc Student, LAMDA Group
School of Artificial Intelligence
National Key Laboratory for Novel Software Technology
Nanjing University, Nanjing 210023, China

Email: huangtj@lamda.nju.edu.cn

Laboratory: Room A304, Shaoyifu Building, Nanjing University Xianlin Campus

Biography

Currently I am a graduate student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou.

I received my B.Eng. degree in Automation from School of Management and Engineering, Nanjing University in June 2022. In September 2022, I was admitted to pursue a M.Sc. degree in Nanjing University, under the supervision of Associate Professor Han-jia Ye and Professor De-Chuan Zhan without entrance examination.

Research Interests

My research interests include Machine Learning and Data Mining. Currently, I focus on learning in extreme environments, including Few-Shot (Meta) Learning and Model Reuse (Transfer of Pre-trained Models). Recently, I am interested in

Learning to Assess Models: A valuable learning paradigm to improve the performance on transfer tasks, especially when only a few labeled transfer data are available.
Large Language Models for Downstream Tasks: Utilize model resources, use the knowledge of pre-trained language models and make models more discriminative, e.g. Modifying vocabularies for Recommendation.

Publications - Conference Papers

Yi-Kai Zhang, Ting-Ji Huang, Yao-Xiang Ding, De-Chuan Zhan, Han-Jia Ye. Model Spider: Learning to Rank Pre-Trained Models Efficiently. [Spotlight] In: Advances in Neural Information Processing Systems 36 (NeurIPS'23), New Orleans, 2023. [Paper] [Code]

We propose Model Spider, which tokenizes pre-trained models (PTMs) and tasks to enable efficient PTM selection. Leveraging PTMs' approximated performance on historical tasks, Model Spider learns to rank with model-task pairs and generalizes to new downstream tasks. PTM-specific task tokens further improves PTM selection. Model Spider balances efficiency and selection ability, demonstrating promising performance in various configurations of model zoos.

Ting-Ji Huang, Qi-Le Zhou, Han-Jia Ye, De-Chuan Zhan. Change Point Detection via Synthetic Signals. Advanced Analytics and Learning on Temporal Data - 8th ECML-PKDD Workshop (AALTD@ECML-PKDD'23), Turin, Italy, 2023. [Paper] [Code]

we introduce a novel approach to change point detection that eliminates the requirement for collecting supervised data. We train a discriminant model using artificially generated synthetic signals comprising a combination of intricate patterns and random noise, which is designed to predict the number of change points. Experimental results demonstrate the superiority of our Detection Model via Synthetic Signals (DMSS) on the Human Activity Segmentation dataset.

Awards and Honors

Kaggle, Human Activity Segmentation Challenge@ECML/PKDD, 2nd place, 2023
Kaggle, Anticipating Vehicle Accidents Challenge@ICME, 2nd place, 2023
Outstanding graduated of Nanjing University, 2022
National Scholarship, 2021

Correspondence

Email: huangtj {AT} lamda.nju.edu.cn

Laboratory: Room A304, Shaoyifu 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.)