3 papers
cs.LG2025
Semantically-Guided Inference for Conditional Diffusion Models: Enhancing Covariate Consistency in Time Series Forecasting
Rui Ding, Hanyang Meng, Zeyang Zhang +1
Diffusion models have demonstrated strong performance in time series forecasting, yet often suffer from semantic misalignment between generated trajectories and conditioning covari…
cs.LG2024
Control the GNN: Utilizing Neural Controller with Lyapunov Stability for Test-Time Feature Reconstruction
Jielong Yang, Rui Ding, Feng Ji +2
The performance of graph neural networks (GNNs) is susceptible to discrepancies between training and testing sample distributions. Prior studies have attempted to mitigating the im…
cs.LG2023
FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstruction
Rui Ding, Jielong Yang, Feng Ji +2
Due to inappropriate sample selection and limited training data, a distribution shift often exists between the training and test sets. This shift can adversely affect the test perf…