Dongyue Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dongyue Chen has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Qinghua Hu
Tianjin University
2 shared publications - Bing Cao
Tianjin University
1 shared publication Emadeldeen Eldele
Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore Institute for InfoComm Research, Agency for Science, Technology and Research, Singapore
1 shared publication- Guosong Jiang
College of Intelligence and Computing and the Tianjin Key Laboratory of Machine Learning, Tianjin University, Tianjin, China
1 shared publication - Pengfei Zhu
School of Automation, Southeast University, Nanjing, China
1 shared publication - Yanru Sun
Tianjin Key Lab of Machine Learning, College of Intelligence and Computing, Tianjin University, China
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (19) , 20743-20751
Hierarchical Classification Auxiliary Network for Time Series Forecasting
Deep learning has significantly advanced time series forecasting through its powerful capacity to capture sequence relationships. However, training these models with the Mean Square Error (MSE) loss often results in over-smooth predictions, making it challenging to handle the complexity and learn high-entropy features from time series data with high variability and unpredictability. In this work, we introduce a novel approach by tokenizing time series values to train forecasting models via cross-entropy loss, while considering the continuous nature of time series data. Specifically, we propose a Hierarchical Classification Auxiliary Network, HCAN, a general model-agnostic component that can be integrated with any forecasting model. HCAN is based on a Hierarchy-Aware Attention module that integrates multi-granularity high-entropy features at different hierarchy levels. At each level, we assign a class label for timesteps to train an Uncertainty-Aware Classifier. This classifier mitigates the over-confidence in softmax loss via evidence theory. We also implement a Hierarchical Consistency Loss to maintain prediction consistency across hierarchy levels. Extensive experiments integrating HCAN with state-of-the-art forecasting models demonstrate substantial improvements over baselines on several real-world datasets.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (19) , 20743-20751
Open AccessHierarchical Classification Auxiliary Network for Time Series Forecasting
Deep learning has significantly advanced time series forecasting through its powerful capacity to capture sequence relationships. However, training these models with the Mean Square Error (MSE) loss often results in over-smooth predictions, making it challenging to handle the complexity and learn high-entropy features from time series data with high variability and unpredictability. In this work, we introduce a novel approach by tokenizing time series values to train forecasting models via cross-entropy loss, while considering the continuous nature of time series data. Specifically, we propose a Hierarchical Classification Auxiliary Network, HCAN, a general model-agnostic component that can be integrated with any forecasting model. HCAN is based on a Hierarchy-Aware Attention module that integrates multi-granularity high-entropy features at different hierarchy levels. At each level, we assign a class label for timesteps to train an Uncertainty-Aware Classifier. This classifier mitigates the over-confidence in softmax loss via evidence theory. We also implement a Hierarchical Consistency Loss to maintain prediction consistency across hierarchy levels. Extensive experiments integrating HCAN with state-of-the-art forecasting models demonstrate substantial improvements over baselines on several real-world datasets.
- 3 March 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 4366-4383
Unknown Support Prototype Set for Open Set Recognition
- 3 March 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 4366-4383
Unknown Support Prototype Set for Open Set Recognition