4 papers
PRISM: Dynamic Primitive-Based Forecasting for Large-Scale GPU Cluster Workloads
Xin Wu, Fei Teng, Xingwang Li +2
Accurately forecasting GPU workloads is essential for AI infrastructure, enabling efficient scheduling, resource allocation, and power management. Modern workloads are highly volat…
Exploring Partial Multi-Label Learning via Integrating Semantic Co-occurrence Knowledge
Xin Wu, Fei Teng, Yue Feng +4
Partial multi-label learning aims to extract knowledge from incompletely annotated data, which includes known correct labels, known incorrect labels, and unknown labels. The core c…
Out-of-Distribution Generalization in Time Series: A Survey
Xin Wu, Fei Teng, Xingwang Li +3
Time series frequently manifest distribution shifts, diverse latent features, and non-stationary learning dynamics, particularly in open and evolving environments. These characteri…
ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification
Xin Wu, Fei Teng, Ji Zhang +2
An ideal time series classification (TSC) should be able to capture invariant representations, but achieving reliable performance on out-of-distribution (OOD) data remains a core o…