Graph Neural Networks: A Review of Methods and Applications（图神经网络：方法与应用综述）

最新推荐文章于 2024-08-19 00:15:00 发布

Adam婷

最新推荐文章于 2024-08-19 00:15:00 发布

阅读量5.3k

点赞数 2

分类专栏： AI程序员机器学习 GNN 论文研读

本文链接：https://blog.csdn.net/weixin_41697507/article/details/94895258

版权

AI程序员同时被 3 个专栏收录

166 篇文章 9 订阅 ¥19.90 ¥99.00

订阅专栏

超级会员免费看

机器学习

161 篇文章 8 订阅 ¥19.90 ¥99.00

订阅专栏

超级会员免费看

论文研读

38 篇文章 1 订阅

订阅专栏

本文详细回顾了图神经网络（GNN）的现有模型，阐述了其在物理系统、化学和生物、知识图谱等多个领域的应用，并提出未来研究的四个开放问题。GNN作为深度学习在非欧几里得数据结构上的拓展，通过节点间的消息传递捕获图形依赖，解决了传统CNN在处理图形数据时的局限性，展现出强大的表现力和可解释性。

摘要由CSDN通过智能技术生成

Graph Neural Networks: A Review of Methods and Applications

图神经网络：方法与应用综述

Jie Zhou , Ganqu Cui , Zhengyan Zhang , Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun

Abstract—Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics system, learning molecular fingerprints, predicting protein interface, and classifying diseases require that a model learns from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures, like the dependency tree of sentences and the scene graph of images, is an important research top