Network Representation Learning Framework Based on Adversarial Graph Convolutional Networks

被引：0

作者：

Chen M. ^{[1
]}

Liu Y. ^{[1
]}

机构：

[1] School of Computer Science and Technology, Heilongjiang University, Harbin

来源：

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2019年 / 32卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Key Words Network Representation; Link Prediction; Multi-task Learning; Node Classification;

D O I：

10.16451/j.cnki.issn1003-6059.201911009

中图分类号：

学科分类号：

摘要：

The existing network representation methods and their related variants are focused on preserving network topology structure or minimizing reconstruction error. However, data distribution of latent codes is ignored. To solve the problem, an adversarial graph convolutional networks(AGCN) is proposed. AGCN combines graph structure information and node attribute information to improve network representation learning performance, and enforces the latent codes to match a prior distribution. Moreover, an end-to-end multi-task learning framework(MTL) based on AGCN is introduced. It can perform link prediction and node classification simultaneously. The experiment shows that MTL achieves a good performance.

引用

页码：1042 / 1050

页数：8

共 25 条

[21]

Lu Q., Getoor L., Link-Based Classification, Proc of the 20th International Conference on Machine Learning, pp. 496-503, (2003)

[22]

Yang Z.L., Cohen W.W., Salakhutdinov R., Et al., Revisiting Semi-supervised Learning with Graph Embeddings

[23]

Zhou T., Lu L.Y., Zhang Y.G., Predicting Missing Links via Local Information, The European Physical Journal B, 71, 4, pp. 623-630, (2009)

[24]

Pan S.R., Hu R.Q., Long G.D., Et al., Adversarially Regularized Graph Autoencoder for Graph Embedding

[25]

Liu P.F., Qiu X.P., Hang X.J., Et al., Recurrent Neural Network for Text Classification with Multi-Task Learning

← 1 2 3 →