所有文章 > 正文

Semi-Supervised Classification with Graph Convolutional Networks

作者: AMiner

浏览量: 200

时间: 2019-01-04 04:05

关键词: 图卷积网络,半监督分类,GCN

周末也不忘记学习系列。
论文名:
Semi-Supervised Classification with Graph Convolutional Networks

作者:Thomas N. Kipf, and Max Welling.

推荐理由:

该论文提出了一种广义图卷积网络的一阶近似方法,并使用对称规范化的方式实现了一种简洁高效的图卷积结构,在处理大规模网络的半监督分类问题上效果显著,仅标注0.1~5%的节点即可实现66~81.5%的分类准确率。同时,作者以空手道俱乐部网络为例,说明了该模型对小规模数据同样有效。该论文发表一年多以来已经有300余次引用量,包括GCN的相关改进,以及GCN在自然语言处理、社交网络分析、生物医学等领域的应用,可以说是研究GCN的“必引论文”。

Abstract

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.

论文下载链接

https://www.aminer.cn/archive/semi-supervised-classification-with-graph-convolutional-networks/58437722ac44360f1082efeb


[关于转载]:本文为AMiner唯一官方微信公众号“学术头条”原创文章。转载仅限全文转载并保留文章标题及内容,不得删改、添加内容绕开原创保护,且文章开头必须注明:转自“SciTouTiao”微信公众号。谢谢您的合作。

扫码微信阅读
[关于转载]:本文转载于AMiner,仅用于学术分享,有任何问题请与我们联系:report@aminer.cn。