6 papers · 1 filter
Contrastive Representation-Guided Genetic Minority Oversampling for Imbalanced Time-Series Classification
Wenbin Pei, Yunrong Hao, Zhen Liu +4
Real-world time-series classification tasks often exhibit class imbalance, which can be extremely severe in some applications. To avoid training biased classifiers on imbalanced da…
Evo-TFS: Evolutionary Time-Frequency Domain-Based Synthetic Minority Oversampling Approach to Imbalanced Time Series Classification
Wenbin Pei, Ruohao Dai, Bing Xue +3
Time series classification is a fundamental machine learning task with broad real-world applications. Although many deep learning methods have proven effective in learning time-ser…
HWL-HIN: A Hypergraph-Level Hypergraph Isomorphism Network as Powerful as the Hypergraph Weisfeiler-Lehman Test with Application to Higher-Order Network Robustness
Chengyu Tian, Wenbin Pei
Robustness in complex systems is of significant engineering and economic importance. However, conventional attack-based a posteriori robustness assessments incur prohibitive comput…
Federated Unlearning Model Recovery in Data with Skewed Label Distributions
Xinrui Yu, Wenbin Pei, Bing Xue +1
In federated learning, federated unlearning is a technique that provides clients with a rollback mechanism that allows them to withdraw their data contribution without training fro…
EvoSampling: A Granular Ball-based Evolutionary Hybrid Sampling with Knowledge Transfer for Imbalanced Learning
Wenbin Pei, Ruohao Dai, Bing Xue +4
Class imbalance would lead to biased classifiers that favor the majority class and disadvantage the minority class. Unfortunately, from a practical perspective, the minority class…
UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba
Li Wu, Wenbin Pei, Jiulong Jiao +1
Multivariate Time series forecasting is crucial in domains such as transportation, meteorology, and finance, especially for predicting extreme weather events. State-of-the-art meth…