当前位置: X-MOL 学术Appl. Soft Comput. › 论文详情
Influence-aware graph neural networks
Applied Soft Computing ( IF 5.472 ) Pub Date : 2021-02-16 , DOI: 10.1016/j.asoc.2021.107169
Bin Yu; Yu Zhang; Yu Xie; Chen Zhang; Ke Pan

Network representation learning endeavors to learn low-dimensional dense representations for nodes in a network. With the rapid development of online social platforms, the analysis of social networks has become increasingly significant. Although network representation learning can facilitate the social network analysis, most existing algorithms merely exploit the explicit structure among nodes to obtain the node representations. Besides, traditional network representation learning techniques ignore the influence of nodes in a network when generating the representations of nodes. Motivated by this, we innovatively propose an influence-aware graph neural network (IAGNN) framework, which can learn the latent feature representations of nodes by incorporating both node influence and global structure information into the embedding process for encoding graph-structured data. The generated low-dimensional dense representations of the nodes in a network can be used for subsequent tasks such as user classification and user behavior prediction. Specifically, we assign different weights to each node according to different types of topology between their neighbors, and integrate with the basic influence of each node to generate an intermediate matrix with influence information. The intermediate matrix is encoded into low-dimensional and dense vector spaces by leveraging the attention mechanism and the graph convolution operation. Extensive experiments are conducted on five datasets, and IAGNN achieves an average accuracy of 3% higher than the comparison algorithms on the node classification and link prediction tasks. The experimental results demonstrate that our model can significantly outperform the state-of-the-art network embedding methods such as GCN, GAT, GraphSage, AGNN on node classification and link prediction tasks.



中文翻译:

影响感知图神经网络

网络表示学习努力学习网络中节点的低维密集表示。随着在线社交平台的快速发展,对社交网络的分析变得越来越重要。尽管网络表示学习可以促进社交网络分析,但是大多数现有算法仅利用节点之间的显式结构来获取节点表示。此外,传统的网络表示学习技术在生成节点表示时会忽略网络中节点的影响。因此,我们创新地提出了一种影响感知图神经网络(IAGNN)框架,通过将节点影响力和全局结构信息合并到用于对图形结构数据进行编码的嵌入过程中,可以学习节点的潜在特征表示。网络中节点的生成的低维密集表示可以用于后续任务,例如用户分类和用户行为预测。具体来说,我们根据邻居之间不同的拓扑类型为每个节点分配不同的权重,并与每个节点的基本影响力集成,以生成一个具有影响信息的中间矩阵。通过利用注意力机制和图卷积运算,将中间矩阵编码为低维和密集向量空间。在五个数据集上进行了广泛的实验,IAGNN的平均准确度比节点分类和链接预测任务上的比较算法高3%。实验结果表明,在节点分类和链接预测任务上,我们的模型可以显着优于最新的网络嵌入方法,例如GCN,GAT,GraphSage,AGNN。

更新日期:2021-02-21
全部期刊列表>>
2021新春特辑
SN Applied Sciences期刊征稿中
虚拟特刊
亚洲大洋洲地球科学
NPJ欢迎投稿
自然科研论文编辑
ERIS期刊投稿
欢迎阅读创刊号
自然职场,为您触达千万科研人才
spring&清华大学出版社
城市可持续发展前沿研究专辑
Springer 纳米技术权威期刊征稿
全球视野覆盖
施普林格·自然新
chemistry
物理学研究前沿热点精选期刊推荐
自然职位线上招聘会
欢迎报名注册2020量子在线大会
化学领域亟待解决的问题
材料学研究精选新
GIANT
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
阿拉丁试剂right
上海中医药大学
哈工大
西湖大学
化学所
北京大学
山东大学
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
南方科技大学
张凤娇
中国石油大学
天合科研
x-mol收录
试剂库存
down
wechat
bug