Výsledky vyhledávání

Report

Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs

Autor: Zhao, Huanjing, Yang, Beining, Cen, Yukuo, Ren, Junyu, Zhang, Chenhui, Dong, Yuxiao, Kharlamov, Evgeny, Zhao, Shu, Tang, Jie

The text-attributed graph (TAG) is one kind of important real-world graph-structured data with each node associated with raw texts. For TAGs, traditional few-shot node classification methods directly conduct training on the pre-processed node feature

Externí odkaz: http://arxiv.org/abs/2407.15431

Zobrazit plný text záznamu

Report

Spatio-Temporal Graph Convolutional Network Combined Large Language Model: A Deep Learning Framework for Bike Demand Forecasting

Autor: Li, Peisen, Pang, Yizhe, Ren, Junyu

This study presents a new deep learning framework, combining Spatio-Temporal Graph Convolutional Network (STGCN) with a Large Language Model (LLM), for bike demand forecasting. Addressing challenges in transforming discrete datasets and integrating u

Externí odkaz: http://arxiv.org/abs/2403.15733

Zobrazit plný text záznamu

Dissertation/ Thesis

Metal-Macrocyclic Frameworks based on Aza-Macrocycles: Design Strategies and Applications

Autor: Ren, Junyu

The present thesis mainly proposes to explore the potential of aza-macrocycles in metal-organic frameworks (MOFs) for applications related to unprecedented open macrocycle cavities. Strategies such as direct arylation of secondary amines as well as m

Externí odkaz: https://digital.library.unt.edu/ark:/67531/metadc1944312/

Zobrazit plný text záznamu