Výsledky vyhledávání - "Zhu, Minhong"

Report

Multiplex Graph Contrastive Learning with Soft Negatives

Autor: Zhao, Zhenhao, Zhu, Minhong, Wang, Chen, Wang, Sijia, Zhang, Jiqiang, Chen, Li, Cai, Weiran

Graph Contrastive Learning (GCL) seeks to learn nodal or graph representations that contain maximal consistent information from graph-structured data. While node-level contrasting modes are dominating, some efforts commence to explore consistency acr

Externí odkaz: http://arxiv.org/abs/2409.08010

Zobrazit plný text záznamu

Report

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

Autor: Bian, Nannan, Zhu, Minhong, Chen, Li, Cai, Weiran

Deep learning methods have been exerting their strengths in long-term time series forecasting. However, they often struggle to strike a balance between expressive power and computational efficiency. Resorting to multi-layer perceptrons (MLPs) provide

Externí odkaz: http://arxiv.org/abs/2405.03199

Zobrazit plný text záznamu

Report

Hybrid Focal and Full-Range Attention Based Graph Transformers

Autor: Zhu, Minhong, Zhao, Zhenhao, Cai, Weiran

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting information

Externí odkaz: http://arxiv.org/abs/2311.04653

Zobrazit plný text záznamu