目录

* 社交网络的表示学习任务 <https://blog.csdn.net/liudingbobo/article/details/83039233#_2>
* 异构图的网络表示 <https://blog.csdn.net/liudingbobo/article/details/83039233#_6>
* 论文1:在异构的社交网络中学习节点的潜在表示[^10]
<https://blog.csdn.net/liudingbobo/article/details/83039233#110_17>
* 论文2:应用于社交网络的异构图形的分类学习[^11]
<https://blog.csdn.net/liudingbobo/article/details/83039233#211_20>
* reference
<https://blog.csdn.net/liudingbobo/article/details/83039233#reference_24>


<>社交网络的表示学习任务


在日常生活中,会遇到许多的社交网络,比如微博等,展现了不同用户与微博内容之间的各种关系,还有论文之中的网络,展现了论文作者,作者研究课题,论文出版杂志社之间的关系。网络表示学习的任务就是学习一种对这些节点的表示方法,以方便其用于机器学习的任务中,如分类,连接预测等
1 <https://blog.csdn.net/liudingbobo/article/details/83039233#fn1>。

<>异构图的网络表示


现在对于同构图的网络表示有更多的研究,不过异构图在生活中使用的更为广泛。异构图指的是图中的节点有不同的形式,图中节点之间的关系也有多种不同的形式。在对异构图的研究中,有以下几种方法:

* 将异构图映射到同构图2 <https://blog.csdn.net/liudingbobo/article/details/83039233#fn2>
3 <https://blog.csdn.net/liudingbobo/article/details/83039233#fn3>4
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn4>5
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn5>
,但是这种方法没有完全的探索不同节点之间,或者他们标签之间的联系,甚至提出了不太实际的假设1
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn1>,所以准确率较低。
* 对不同类型的节点使用不同类型的编码6
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn6>。
* 用特定类型的参数来扩展成对的解码器(这句话我现在也不知道什么意思,求赐教)7
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn7>8
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn8>。
* 还有一种是对random walks的扩展9
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn9>。
对于异构网络的表示学习的研究,我最近看了两篇论文,其中一篇是另一篇的改进版本。

<>论文1:在异构的社交网络中学习节点的潜在表示10
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn10>

<>论文2:应用于社交网络的异构图形的分类学习11
<https://blog.csdn.net/liudingbobo/article/details/83039233#fn11>

<>reference

*
Jacob Y, Denoyer L, Gallinari P. Learning latent representations of nodes for
classifying in heterogeneous social networks[C]// ACM, 2014:373-382.↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref1> ↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref1:1>

*
Belkin M, Niyogi P, Sindhwani V. Manifold Regularization: A Geometric
Framework for Learning from Labeled and Unlabeled Examples[M].JMLR.org
<http://JMLR.org>, 2006. ↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref2>

*
Sofus A. Macskassy and Foster Provost. A simple relational classi fier. In
Proceedings of the Second Workshop on Multi-Relational Data Mining (MRDM-2003)
at KDD-2003, pages 64{76, 2003.↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref3>

*
Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Gallagher,
and Tina Eliassi-Rad. Collective classi cation in network data. AI Magazine,
29(3):93{106, 2008.↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref4>

*
Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, and Bernhard
Scholkopf. Learning with local and global consistency. In Sebastian Thrun,
Lawrence Saul, and Bernhard Scholkopf, editors, Advances in Neural Inform.
Process. Systems 16. 2004.↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref5>

*
Chang, S.; Han, W.; Tang, J.; Qi, G. J.; Aggarwal, C. C. & Huang, T. S.
Heterogeneous Network Embedding via Deep Architectures. Acm Sigkdd
International Conference on Knowledge Discovery & Data Mining, 2015, 119-128↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref6>

*
Nickel, M.; Murphy, K.; Tresp, V. & Gabrilovich, E. A Review of Relational
Machine Learning for Knowledge Graphs. Proceedings of the IEEE, 2015, 104, 11-33
↩︎ <https://blog.csdn.net/liudingbobo/article/details/83039233#fnref7>

*
Schlichtkrull, M.; Kipf, T. N.; Bloem, P.; Berg, R. V. D.; Titov, I. &
Welling, M. Modeling Relational Data with Graph Convolutional Networks. 2017,
593-607↩︎ <https://blog.csdn.net/liudingbobo/article/details/83039233#fnref8>

*
Swami, A.; Swami, A. & Swami, A. metapath2vec: Scalable Representation
Learning for Heterogeneous Networks. ACM SIGKDD International Conference on
Knowledge Discovery and Data Mining, 2017, 135-144↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref9>

*
Jacob, Y.; Denoyer, L. & Gallinari, P. Learning latent representations of
nodes for classifying in heterogeneous social networks. 2014, 13, 373-382↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref10>

*
Santos, L. D.; Piwowarski, B.; Denoyer, L. & Gallinari, P. Representation
Learning for Classification in Heterogeneous Graphs with Application to Social
Networks. ACM Trans. Knowl. Discov. Data, ACM, 2018, 12, 62:1-62:33↩︎
<https://blog.csdn.net/liudingbobo/article/details/83039233#fnref11>