3 papers
cs.LG2024
How Much Can Time-related Features Enhance Time Series Forecasting?
Chaolv Zeng, Yuan Tian, Guanjie Zheng +1
Recent advancements in long-term time series forecasting (LTSF) have primarily focused on capturing cross-time and cross-variate (channel) dependencies within historical data. Howe…
cs.LG2024
CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting
Chaolv Zeng, Zhanyu Liu, Guanjie Zheng +1
Recent advancements in multivariate time series forecasting have been propelled by Linear-based, Transformer-based, and Convolution-based models, with Transformer-based architectur…
cs.LG2024
Graph Data Condensation via Self-expressive Graph Structure Reconstruction
Zhanyu Liu, Chaolv Zeng, Guanjie Zheng
With the increasing demands of training graph neural networks (GNNs) on large-scale graphs, graph data condensation has emerged as a critical technique to relieve the storage and t…