Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting

1 code implementation • 6 May 2024 • Nannan Bian, Minhong Zhu, Li Chen, Weiran Cai

Deep learning methods have been exerting their strengths in long-term time series forecasting.

Computational Efficiency Time Series +1

Hybrid Focal and Full-Range Attention Based Graph Transformers

no code implementations • 8 Nov 2023 • Minhong Zhu, Zhenhao Zhao, Weiran Cai

The core component of FFGT is a new mechanism of compound attention, which combines the conventional full-range attention with K-hop focal attention on ego-nets to aggregate both global and local information.