Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE

no code implementations • 3 Jun 2024 • Jiaxu Liu, Xinping Yi, Sihao Wu, Xiangyu Yin, Tianle Zhang, Xiaowei Huang, Jin Shi

While Hyperbolic Graph Neural Network (HGNN) has recently emerged as a powerful tool dealing with hierarchical graph data, the limitations of scalability and efficiency hinder itself from generalizing to deep models.

Graph Neural Network Image-text Classification +4

WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset

no code implementations • 29 Feb 2024 • Jiantao Qiu, Haijun Lv, Zhenjiang Jin, Rui Wang, Wenchang Ning, JIA YU, Chaobin Zhang, Zhenxiang Li, Pei Chu, Yuan Qu, Jin Shi, Lindong Lu, Runyu Peng, Zhiyuan Zeng, Huanze Tang, Zhikai Lei, Jiawei Hong, Keyu Chen, Zhaoye Fei, Ruiliang Xu, Wei Li, Zhongying Tu, Lin Dahua, Yu Qiao, Hang Yan, Conghui He

To evaluate the quality and utility of the dataset, we trained 1B-parameter and 3B-parameter models using WanJuan-CC and another dataset, RefinedWeb.

Deep Learning for MIMO Channel Estimation: Interpretation, Performance, and Comparison

no code implementations • 5 Nov 2019 • Hu Qiang, Gao Feifei, Zhang Hao, Jin Shi, Li Geoffrey Ye

Deep learning (DL) has emerged as an effective tool for channel estimation in wireless communication systems, especially under some imperfect environments.