12 accepted papers
Multivariate time series (MTS) forecasting critically depends on modeling inter-variable dependencies, yet existing paradigms face a trade-off: channel-isolation strategies can suffer from information fragmentation in strongly coupled systems, whereas channel-interaction methods often introduce spur…
Spatiotemporal traffic forecasting currently faces dual challenges: capturing long-range periodic dependencies and managing the computational burden of increasingly complex deep neural network architectures. Mainstream models typically contain millions of parameters and struggle to handle long seque
Graph Neural Networks (GNNs) have advanced graph classification, yet they remain vulnerable to graph-level imbalance, encompassing class imbalance and topological imbalance. To address both types of imbalance in a unified manner, we propose UniImb, a Unified framework for Imbalanced graph classifica…
While existing multivariate time series forecasting models have advanced significantly in modeling periodicity, they largely neglect the periodic heterogeneity common in real-world data, where variables exhibit distinct and dynamically changing periods. To effectively capture this periodic heterogen…
Accurate weather forecasting is crucial for climate research, disaster mitigation, and societal planning. Despite recent progress with deep learning, global atmospheric data remain uniquely challenging since weather dynamics evolve across heterogeneous spatial and temporal scales ranging from planet…
Current mainstream research in multivariate time series (MTS) prediction often assumes that all data is static. However, real-world MTS data typically arrives continuously in a streaming manner, which we refer to as streaming MTS. The statistical characteristics and spatiotemporal graph topology of
Graph classification is a critical task in analyzing graph data, with applications across various domains. While graph neural networks (GNNs) have achieved remarkable results, their ability to generalize across graphs of varying scales remains a challenge. Conventional models often perform well on l
Air quality prediction plays a crucial role in the development of smart cities, garnering significant attention from both academia and industry. Current air quality prediction models encounter two major limitations: their high computational complexity limits scalability to nationwide datasets, and t
The effectiveness of Spatiotemporal Graph Neural Networks (STGNNs) critically hinges on the quality of the underlying graph topology. While end-to-end adaptive graph learning methods have demonstrated promising results in capturing latent spatiotemporal dependencies, they often suffer from high comp…
The stable periodic patterns present in the time series data serve as the foundation for long-term forecasting. However, existing models suffer from limitations such as continuous and chaotic input partitioning, as well as weak inductive biases, which restrict their ability to capture such recurring…
Recently, spatiotemporal graph convolutional networks have achieved dominant performance in spatiotemporal prediction tasks. However, most models relying on node-to-node messaging interaction exhibit sensitivity to spatiotemporal shifts, encountering out-of-distribution (OOD) challenges. To address…
Due to the profound impact of air pollution on human health, livelihoods, and economic development, air quality forecasting is of paramount significance. Initially, we employ the causal graph method to scrutinize the constraints of existing research in comprehensively modeling the causal relationshi…