With the phenomenal success of networking sites (<i>e.g.</i>, Facebook, Twitter and LinkedIn), social networks have drawn substantial attention. On online social networking sites, link recommendation is a critical task that not only helps improve user experience but also plays an essential role in network growth. In this paper we propose several link recommendation criteria, based on both <i>user attributes</i> and <i>graph structure</i>. To discover the candidates that satisfy these criteria, link relevance is estimated using a random walk algorithm on an augmented social graph with both attribute and structure information. The global and local influence of the attributes is leveraged in the framework as well. Besides link recommendation, our framework can also rank attributes in a social network. Experiments on DBLP and IMDB data sets demonstrate that our method outperforms state-of-the-art methods based on network structure and node attribute information for link recommendation.
%0 Conference Paper
%1 yin2010
%A Yin, Zhijun
%A Gupta, Manish
%A Weninger, Tim
%A Han, Jiawei
%B Proceedings of the 19th International Conference on World Wide Web (WWW 2010)
%C New York, NY, USA
%D 2010
%I ACM
%K mining ontology
%P 1211--1212
%R 10.1145/1772690.1772879
%T LINKREC: A Unified Framework for Link Recommendation with User Attributes and Graph Structure
%U http://doi.acm.org/10.1145/1772690.1772879
%X With the phenomenal success of networking sites (<i>e.g.</i>, Facebook, Twitter and LinkedIn), social networks have drawn substantial attention. On online social networking sites, link recommendation is a critical task that not only helps improve user experience but also plays an essential role in network growth. In this paper we propose several link recommendation criteria, based on both <i>user attributes</i> and <i>graph structure</i>. To discover the candidates that satisfy these criteria, link relevance is estimated using a random walk algorithm on an augmented social graph with both attribute and structure information. The global and local influence of the attributes is leveraged in the framework as well. Besides link recommendation, our framework can also rank attributes in a social network. Experiments on DBLP and IMDB data sets demonstrate that our method outperforms state-of-the-art methods based on network structure and node attribute information for link recommendation.
%@ 978-1-60558-799-8
@inproceedings{yin2010,
abstract = {With the phenomenal success of networking sites (<i>e.g.</i>, Facebook, Twitter and LinkedIn), social networks have drawn substantial attention. On online social networking sites, link recommendation is a critical task that not only helps improve user experience but also plays an essential role in network growth. In this paper we propose several link recommendation criteria, based on both <i>user attributes</i> and <i>graph structure</i>. To discover the candidates that satisfy these criteria, link relevance is estimated using a random walk algorithm on an augmented social graph with both attribute and structure information. The global and local influence of the attributes is leveraged in the framework as well. Besides link recommendation, our framework can also rank attributes in a social network. Experiments on DBLP and IMDB data sets demonstrate that our method outperforms state-of-the-art methods based on network structure and node attribute information for link recommendation.},
acmid = {1772879},
added-at = {2011-10-04T16:07:21.000+0200},
address = {New York, NY, USA},
author = {Yin, Zhijun and Gupta, Manish and Weninger, Tim and Han, Jiawei},
biburl = {https://www.bibsonomy.org/bibtex/29ceecd5070f1b14c7cd182be96e88bbf/utahell},
booktitle = {Proceedings of the 19th International Conference on World Wide Web (WWW 2010)},
description = {LINKREC},
doi = {10.1145/1772690.1772879},
interhash = {edfb2f2f8e200d8fdce2ce2c2a758edb},
intrahash = {9ceecd5070f1b14c7cd182be96e88bbf},
isbn = {978-1-60558-799-8},
keywords = {mining ontology},
location = {Raleigh, North Carolina, USA},
numpages = {2},
pages = {1211--1212},
publisher = {ACM},
series = {WWW '10},
timestamp = {2011-12-14T18:46:55.000+0100},
title = {LINKREC: A Unified Framework for Link Recommendation with User Attributes and Graph Structure},
url = {http://doi.acm.org/10.1145/1772690.1772879},
year = 2010
}