3 papers
cs.LG2026
FAiT: Frequency-Aware Inverted Transformer for Multivariate Time Series Forecasting
Peng He, Yao Liu, Yanglei Gan +3
While Transformer-based architectures have established themselves as a dominant paradigm in Multivariate Time Series Forecasting (MTSF), their core self-attention mechanism inheren…
cs.LG2026
GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes
Guanyu Zhou, Yao Liu, Yanglei Gan +5
Spatio-temporal point processes (STPPs) provide a principled framework for modeling asynchronous events in continuous time and space. Recent diffusion-based approaches offer a flex…
cs.AI2026
Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation
Yanglei Gan, Peng He, Yuxiang Cai +3
Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their abilit…