3 papers
cs.LG2026
DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors
Jiale Deng, Yanyan Shen, Xiaogang Shi +1
High-quality training data is essential for the success of machine learning models. However, real-world datasets often contain mixed types of errors arising from systematic flaws i…
cs.LG2024
Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting
Lifan Zhao, Yanyan Shen
Time series forecasting always faces the challenge of concept drift, where data distributions evolve over time, leading to a decline in forecast model performance. Existing solutio…
cs.LG2024
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
Lifan Zhao, Yanyan Shen
Recently, channel-independent methods have achieved state-of-the-art performance in multivariate time series (MTS) forecasting. Despite reducing overfitting risks, these methods mi…