11 papers
Scalable Graph Condensation with Evolving Capabilities
Shengbo Gong, Mohammad Hashemi, Juntong Ni +2
The rapid growth of graph data creates significant scalability challenges as most graph algorithms scale quadratically with size. To mitigate these issues, Graph Condensation (GC)…
Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?
Zewen Liu, Juntong Ni, Xianfeng Tang +4
Uncovering hidden symbolic laws from time series data, as an aspiration dating back to Kepler's discovery of planetary motion, remains a core challenge in scientific discovery and…
STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning
Juntong Ni, Shiyu Wang, Qi He +2
Spatio-temporal reasoning in time series involves the explicit synthesis of temporal dynamics, spatial dependencies, and textual context. This capability is vital for high-stakes d…
TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
Zhiyuan Zhao, Juntong Ni, Shangqing Xu +3
Time-series forecasting is an essential task with wide real-world applications across domains. While recent advances in deep learning have enabled time-series forecasting models wi…
Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes
Zewen Liu, Juntong Ni, Bohan Wang +2
Accurate epidemic forecasting is crucial for outbreak preparedness, but existing data-driven models are often brittle. Typically trained on a single pathogen, they struggle with da…
TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation
Juntong Ni, Zewen Liu, Shiyu Wang +2
Transformer-based and CNN-based methods demonstrate strong performance in long-term time series forecasting. However, their high computational and storage requirements can hinder l…