Non-Linear Smoothed Transductive Network Embedding with Text Information

Weizheng Chen, Xia Zhang, Jinpeng Wang, Yan Zhang, Hongfei Yan, Xiaoming Li
; Proceedings of The 8th Asian Conference on Machine Learning, PMLR 63:1-16, 2016.

Abstract

Network embedding is a classical task which aims to map the nodes of a network to low-dimensional vectors. Most of the previous network embedding methods are trained in an unsupervised scheme. Then the learned node embeddings can be used as inputs of many machine learning tasks such as node classification, attribute inference. However, the discrimination validity of the node embeddings maybe improved by considering the node label information and the node attribute information. Inspired by traditional semi-supervised learning techniques, we explore to train the node embeddings and the node classifiers simultaneously with the text attributes information in a flexible framework. We present NLSTNE (Non-Linear Smoothed Transductive Network Embedding), a transductive network embedding method, whose embeddings are enhanced by modeling the non-linear pairwise similarity between the nodes and the non-linear relationship between the nodes and the text attributes. We use the node classification task to evaluate the quality of node embeddings learned by different models on four real-world network datasets . The experimental results demonstrate that our model outperforms several state-of-the-art network embedding methods.

Cite this Paper


BibTeX
@InProceedings{pmlr-v63-chen115, title = {Non-Linear Smoothed Transductive Network Embedding with Text Information}, author = {Weizheng Chen and Xia Zhang and Jinpeng Wang and Yan Zhang and Hongfei Yan and Xiaoming Li}, booktitle = {Proceedings of The 8th Asian Conference on Machine Learning}, pages = {1--16}, year = {2016}, editor = {Robert J. Durrant and Kee-Eung Kim}, volume = {63}, series = {Proceedings of Machine Learning Research}, address = {The University of Waikato, Hamilton, New Zealand}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v63/chen115.pdf}, url = {http://proceedings.mlr.press/v63/chen115.html}, abstract = {Network embedding is a classical task which aims to map the nodes of a network to low-dimensional vectors. Most of the previous network embedding methods are trained in an unsupervised scheme. Then the learned node embeddings can be used as inputs of many machine learning tasks such as node classification, attribute inference. However, the discrimination validity of the node embeddings maybe improved by considering the node label information and the node attribute information. Inspired by traditional semi-supervised learning techniques, we explore to train the node embeddings and the node classifiers simultaneously with the text attributes information in a flexible framework. We present NLSTNE (Non-Linear Smoothed Transductive Network Embedding), a transductive network embedding method, whose embeddings are enhanced by modeling the non-linear pairwise similarity between the nodes and the non-linear relationship between the nodes and the text attributes. We use the node classification task to evaluate the quality of node embeddings learned by different models on four real-world network datasets . The experimental results demonstrate that our model outperforms several state-of-the-art network embedding methods.} }
Endnote
%0 Conference Paper %T Non-Linear Smoothed Transductive Network Embedding with Text Information %A Weizheng Chen %A Xia Zhang %A Jinpeng Wang %A Yan Zhang %A Hongfei Yan %A Xiaoming Li %B Proceedings of The 8th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Robert J. Durrant %E Kee-Eung Kim %F pmlr-v63-chen115 %I PMLR %J Proceedings of Machine Learning Research %P 1--16 %U http://proceedings.mlr.press %V 63 %W PMLR %X Network embedding is a classical task which aims to map the nodes of a network to low-dimensional vectors. Most of the previous network embedding methods are trained in an unsupervised scheme. Then the learned node embeddings can be used as inputs of many machine learning tasks such as node classification, attribute inference. However, the discrimination validity of the node embeddings maybe improved by considering the node label information and the node attribute information. Inspired by traditional semi-supervised learning techniques, we explore to train the node embeddings and the node classifiers simultaneously with the text attributes information in a flexible framework. We present NLSTNE (Non-Linear Smoothed Transductive Network Embedding), a transductive network embedding method, whose embeddings are enhanced by modeling the non-linear pairwise similarity between the nodes and the non-linear relationship between the nodes and the text attributes. We use the node classification task to evaluate the quality of node embeddings learned by different models on four real-world network datasets . The experimental results demonstrate that our model outperforms several state-of-the-art network embedding methods.
RIS
TY - CPAPER TI - Non-Linear Smoothed Transductive Network Embedding with Text Information AU - Weizheng Chen AU - Xia Zhang AU - Jinpeng Wang AU - Yan Zhang AU - Hongfei Yan AU - Xiaoming Li BT - Proceedings of The 8th Asian Conference on Machine Learning PY - 2016/11/20 DA - 2016/11/20 ED - Robert J. Durrant ED - Kee-Eung Kim ID - pmlr-v63-chen115 PB - PMLR SP - 1 DP - PMLR EP - 16 L1 - http://proceedings.mlr.press/v63/chen115.pdf UR - http://proceedings.mlr.press/v63/chen115.html AB - Network embedding is a classical task which aims to map the nodes of a network to low-dimensional vectors. Most of the previous network embedding methods are trained in an unsupervised scheme. Then the learned node embeddings can be used as inputs of many machine learning tasks such as node classification, attribute inference. However, the discrimination validity of the node embeddings maybe improved by considering the node label information and the node attribute information. Inspired by traditional semi-supervised learning techniques, we explore to train the node embeddings and the node classifiers simultaneously with the text attributes information in a flexible framework. We present NLSTNE (Non-Linear Smoothed Transductive Network Embedding), a transductive network embedding method, whose embeddings are enhanced by modeling the non-linear pairwise similarity between the nodes and the non-linear relationship between the nodes and the text attributes. We use the node classification task to evaluate the quality of node embeddings learned by different models on four real-world network datasets . The experimental results demonstrate that our model outperforms several state-of-the-art network embedding methods. ER -
APA
Chen, W., Zhang, X., Wang, J., Zhang, Y., Yan, H. & Li, X.. (2016). Non-Linear Smoothed Transductive Network Embedding with Text Information. Proceedings of The 8th Asian Conference on Machine Learning, in PMLR 63:1-16

Related Material