Shenghe Zheng is a second-year master degree candidate at the Department of Computer Science, Harbin Institute of Technology, fortunately advised by Prof.Hongzhi Wang. Previously, Shenghe Zheng obtained his Bachelor’s degree from Harbin Institute of Technology in June 2023.
His current research interests lie in Efficient AI, Neural Architecture Search(NAS), and Graph Neural Network(GNN). If you are seeking any form of academic cooperation, please feel free to email at shenghez.zheng@gmail.com.
📖 Educations
- 2023.08 - now, Master Candidate in Computer Science, Harbin Institute of Technology.
- Supervisor: Prof. Hongzhi wang, Rank: 1/129.
- 2019.08 - 2023.06, B.Eng. in Computer Science, Harbin Institute of Technology.
🔥 News
- 2024.09: 🎉 Our IntraMix is accepted by NeurIPS 2024.
📝 Publications
IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
Shenghe Zheng, Hongzhi Wang, Xianglong Liu. Code
- This paper introduces IntraMix, seamlessly applying Mixup to graph augmentation, enhancing model effectiveness in data-scarce scenarios.
DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning
Shenghe Zheng, Hongzhi Wang, Tianyu Mu. Code
- This paper introduces contrastive and curriculum learning for neural predictors, greatly reducing the performance evaluation cost in NAS.
AutoTSC: Optimization Algorithm to Automatically Solve the Time Series Classification Problem
Tianyu Mu, Hongzhi Wang, Shenghe Zheng
- This paper introduces AutoML to time series classification, using dataset similarity to recommend algorithms for new datasets automatically.
Assassin: an automatic classification system based on algorithm selection
Tianyu Mu, Hongzhi Wang, Shenghe Zheng
- This paper uses reinforcement learning to select meta-features and recommend algorithms with hyperparameters for new datasets automatically.
📝 Preprint
FREE-Merging: Fourier Transform for Model Merging with Lightweight Experts
Shenghe Zheng, Hongzhi Wang,
- We find that task-specific information from fine-tuning harms Model Merging, so we use frequency-domain filtering to reduce conflicts and utilize lightweight experts to compensate for information loss during model merging.
🎖 Honors and Awards
- National Scholarship, 2024
- Tencent Scholarship, 2024
- Outstanding Graduate of Harbin Institute of Technology, 2023
- Second Prize at the 14th Undergraduate Academic Forum, Harbin Institute of Technology, 2021
- Honorable Award in American Mathematics Modelling Contest for College Students, 2021
- Outstanding Student of Harbin Institute of Technology, 2019-2024
- Renmin Scholarship, 2019-2022