当前位置: X-MOL 学术Knowl. Inf. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Word and graph attention networks for semi-supervised classification
Knowledge and Information Systems ( IF 2.7 ) Pub Date : 2021-09-08 , DOI: 10.1007/s10115-021-01610-3
Jing Zhang 1 , Mengxi Li 1 , Kaisheng Gao 1 , Shunmei Meng 1 , Cangqi Zhou 1
Affiliation  

Graph attention networks are effective graph neural networks that perform graph embedding for semi-supervised learning, which considers the neighbors of a node when learning its features. This paper presents a novel attention-based graph neural network that introduces an attention mechanism in the word-represented features of a node together incorporating the neighbors’ attention in the embedding process. Instead of using a vector as the feature of a node in the traditional graph attention networks, the proposed method uses a 2D matrix to represent a node, where each row in the matrix stands for a different attention distribution against the original word-represented features of a node. Then, the compressed features are fed into a graph attention layer that aggregates the matrix representation of the node and its neighbor nodes with different attention weights as a new representation. By stacking several graph attention layers, it obtains the final representation of nodes as matrices, which considers both that the neighbors of a node have different importance and that the words also have different importance in their original features. Experimental results on three citation network datasets show that the proposed method significantly outperforms eight state-of-the-art methods in semi-supervised classification tasks.



中文翻译:

用于半监督分类的词和图注意力网络

图注意力网络是有效的图神经网络,它为半监督学习执行图嵌入,在学习其特征时考虑节点的邻居。本文提出了一种新颖的基于注意力的图神经网络,该网络在节点的词表示特征中引入了注意力机制,并在嵌入过程中结合了邻居的注意力。与传统图注意力网络中使用向量作为节点的特征不同,所提出的方法使用二维矩阵来表示节点,其中矩阵中的每一行代表不同的注意力分布相对于原始词表示的特征一个节点。然后,压缩后的特征被送入图注意力层,该层将具有不同注意力权重的节点及其相邻节点的矩阵表示聚合为新的表示。通过堆叠几个图注意力层,它得到节点的最终表示为矩阵,它既考虑了一个节点的邻居具有不同的重要性,也考虑到单词在其原始特征中的重要性也不同。在三个引文网络数据集上的实验结果表明,所提出的方法在半监督分类任务中明显优于八种最先进的方法。它考虑了节点的邻居具有不同的重要性,并且单词在其原始特征中也具有不同的重要性。在三个引文网络数据集上的实验结果表明,所提出的方法在半监督分类任务中明显优于八种最先进的方法。它考虑了节点的邻居具有不同的重要性,并且单词在其原始特征中也具有不同的重要性。在三个引文网络数据集上的实验结果表明,所提出的方法在半监督分类任务中明显优于八种最先进的方法。

更新日期:2021-09-09
down
wechat
bug