5 papers
A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
Yiyuan Yang, Ming Jin, Haomin Wen +9
Diffusion models have been widely used in time series and spatio-temporal data, enhancing generative, inferential, and downstream capabilities. These models are applied across dive…
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
Langzhang Liang, Fanchen Bu, Zixing Song +3
The message-passing paradigm of Graph Neural Networks often struggles with exchanging information across distant nodes typically due to structural bottlenecks in certain graph regi…
Time Series Analysis for Education: Methods, Applications, and Future Directions
Shengzhong Mao, Chaoli Zhang, Yichi Song +4
Recent advancements in the collection and analysis of sequential educational data have brought time series analysis to a pivotal position in educational research, highlighting its…
Intelligent Cross-Organizational Process Mining: A Survey and New Perspectives
Yiyuan Yang, Zheshun Wu, Yong Chu +3
Process mining, as a high-level field in data mining, plays a crucial role in enhancing operational efficiency and decision-making across organizations. In this survey paper, we de…
Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
Langzhang Liang, Sunwoo Kim, Kijung Shin +3
Graph Neural Networks (GNNs) have gained significant attention as a powerful modeling and inference method, especially for homophilic graph-structured data. To empower GNNs in hete…