5 papers
Rethinking Time Series Tokenization from a Frequency Perspective
Zelong Tian, Ming Jin, Bo Du +1
Tokenization that partitions time series into subsequences has become a foundational paradigm in modern time series modeling. However, we find that current tokenization strategies…
TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series
Sheng Pan, Yongli Gu, Yiqing Guo +4
Real-world time series evolve continuously, with meaningful changes potentially emerging at any moment. However, existing time-series language models (TSLMs) remain inherently stat…
LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
Sheng Pan, Ming Jin, Bo Du +1
Time series forecasting serves as an essential tool for many real-world applications, supporting tasks such as resource optimization and decision-making. Despite significant archit…
EventTSF: Event-Aware Non-Stationary Time Series Forecasting
Yunfeng Ge, Ming Jin, Yiji Zhao +4
Time series forecasting is vital in diverse sectors such as energy and transportation, where non-stationary dynamics are deeply intertwined with external events in other modalities…
Online GNN Evaluation Under Test-time Graph Distribution Shifts
Xin Zheng, Dongjin Song, Qingsong Wen +2
Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and…