Výsledky vyhledávání

Report

Non-Euclidean Mixture Model for Social Network Embedding

Autor: Iyer, Roshni G., Wang, Yewen, Wang, Wei, Sun, Yizhou

It is largely agreed that social network links are formed due to either homophily or social influence. Inspired by this, we aim at understanding the generation of links via providing a novel embedding-based graph formation model. Different from exist

Externí odkaz: http://arxiv.org/abs/2411.04876

Zobrazit plný text záznamu

Report

A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware

Autor: Zhang, Shichang, Sohrabizadeh, Atefeh, Wan, Cheng, Huang, Zijie, Hu, Ziniu, Wang, Yewen, Yingyan, Lin, Cong, Jason, Sun, Yizhou

Graph neural networks (GNNs) are emerging for machine learning research on graph-structured data. GNNs achieve state-of-the-art performance on many tasks, but they face scalability challenges when it comes to real-world applications that have numerou

Externí odkaz: http://arxiv.org/abs/2306.14052

Zobrazit plný text záznamu

Report

Autor: Ren, Zhicheng, Yuan, Yifu, Wu, Yuxin, Gao, Xiaxuan, Wang, Yewen, Sun, Yizhou

Training labels for graph embedding algorithms could be costly to obtain in many practical scenarios. Active learning (AL) algorithms are very helpful to obtain the most useful labels for training while keeping the total number of label queries under

Externí odkaz: http://arxiv.org/abs/2212.01968

Zobrazit plný text záznamu