Research
My PhD research focuses on deep learning techniques for processing and analysing complex sequential and structural data, uncovering their intrinsic relationships. Specifically, I investigate methodologies for effective representation learning from these data types, aiming to enhance uncertainty analysis, future prediction, and risk assessment. This includes various approaches such as large-scale data mining, uncertainty estimation, noisy label learning, meta-learning, and domain generalisation, delivering tools for application domains including traffic forecasting and neuromorphic computing.
If you are interested in my research, feel free to drop me an email.
|
A Memory-augmented Conditional Neural Process model for traffic prediction
Ye Wei, He Haitao, Kunhao Yuan, Gerald Schaefer, Zhigang Ji, Hui Fang
Knowledge-Based Systems, 2024
|
Memory-facilitated Joint-space Shift Adaptation in Traffic Forecasting
Ye Wei, He Haitao, Gerald Schaefer, Zhigang Ji, Yifan Wang, Hui Fang
International Joint Conference on Neural Networks, 2024
|
Traffic4cast at NeurIPS 2022 predict dynamics along graph edges from sparse node
data: Whole city traffic and eta from stationary vehicle detectors
Moritz Neun, Christian Eichenberger, Henry Martin, Markus Spanring, Rahul Siripurapu, Daniel Springer, Leyan Deng, Chenwang Wu, Defu Lian, Min Zhou, Martin Lumiste, Andrei Ilie, Xinhua Wu, Cheng Lyu, Qing-Long Lu, Vishal Mahajan, Yichao Lu, Jiezhang Li, Junjun Li, Yue-Jiao Gong, Florian Grötschla, Joël Mathys, Ye Wei, He Haitao, Hui Fang, Kevin Malm, Fei Tang, Michael Kopp, David Kreil, Sepp Hochreiter
NeurIPS Competition Track, 2022
|
Spatial-temporal City-scale Congestion Prediction using a two-stream Graph Neural Network
Ye Wei, He Haitao, Hui Fang
NeurIPS Traffic4cast Competition Technical Report, 2022
|
|