3 papers
cs.AI2026
FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting
Qianyang Li, Xingjun Zhang, Shaoxun Wang +2
Large-scale retail and industrial forecasting systems contain many heterogeneous time series whose lifecycle, sparsity, volatility, seasonality, spectral patterns, and contextual s…
cs.DC2024
Dual-pronged deep learning preprocessing on heterogeneous platforms with CPU, Accelerator and CSD
Jia Wei, Xingjun Zhang, Witold Pedrycz +2
For image-related deep learning tasks, the first step often involves reading data from external storage and performing preprocessing on the CPU. As accelerator speed increases and…
cs.LG2024
BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion
Jia Wei, Xingjun Zhang, Witold Pedrycz
Bagging has achieved great success in the field of machine learning by integrating multiple base classifiers to build a single strong classifier to reduce model variance. The perfo…