Výsledky vyhledávání

Report

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

Autor: Song, Wei, Li, Yadong, Xu, Jianhua, Wu, Guowei, Ming, Lingfeng, Yi, Kexin, Luo, Weihua, Li, Houyi, Du, Yi, Guo, Fangda, Yu, Kaicheng

As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benc

Externí odkaz: http://arxiv.org/abs/2406.05343

Zobrazit plný text záznamu

Report

GIPA: A General Information Propagation Algorithm for Graph Learning

Autor: Li, Houyi, Chen, Zhihong, Li, Zhao, Zheng, Qinkai, Zhang, Peng, Zhou, Shuigeng

Graph neural networks (GNNs) have been widely used in graph-structured data computation, showing promising performance in various applications such as node classification, link prediction, and network recommendation. Existing works mainly focus on no

Externí odkaz: http://arxiv.org/abs/2301.08209

Zobrazit plný text záznamu

Report

Path-based Deep Network for Candidate Item Matching in Recommenders

Autor: Li, Houyi, Chen, Zhihong, Li, Chenliang, Xiao, Rong, Deng, Hongbo, Zhang, Peng, Liu, Yongchao, Tang, Haihong

The large-scale recommender system mainly consists of two stages: matching and ranking. The matching stage (also known as the retrieval step) identifies a small fraction of relevant items from billion-scale item corpus in low latency and computationa

Externí odkaz: http://arxiv.org/abs/2105.08246

Zobrazit plný text záznamu

Report

GIPA: General Information Propagation Algorithm for Graph Learning

Autor: Zheng, Qinkai, Li, Houyi, Zhang, Peng, Yang, Zhixiong, Zhang, Guowei, Zeng, Xintan, Liu, Yongchao

Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. In this paper, we present a new graph

Externí odkaz: http://arxiv.org/abs/2105.06035

Zobrazit plný text záznamu

Report

GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy

Autor: Liu, Yongchao, Li, Houyi, Zhang, Guowei, Zeng, Xintan, Li, Yongyong, Huang, Bin, Zhang, Peng, Li, Zhao, Zhu, Xiaowei, He, Changhua, Chen, Wenguang

Graph neural networks (GNNs) have been demonstrated as a powerful tool for analyzing non-Euclidean graph data. However, the lack of efficient distributed graph learning systems severely hinders applications of GNNs, especially when graphs are big and

Externí odkaz: http://arxiv.org/abs/2104.10569

Zobrazit plný text záznamu