%0 Conference Paper %1 Leroy:2010:CSL:1835804.1835855 %A Leroy, Vincent %A Cambazoglu, B. Barla %A Bonchi, Francesco %B Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining %C New York, NY, USA %D 2010 %I ACM %K thema:exploiting_place_features_in_link_prediction_on_location-based_social_networks %P 393--402 %R 10.1145/1835804.1835855 %T Cold Start Link Prediction %U http://doi.acm.org/10.1145/1835804.1835855 %X In the traditional link prediction problem, a snapshot of a social network is used as a starting point to predict, by means of graph-theoretic measures, the links that are likely to appear in the future. In this paper, we introduce cold start link prediction as the problem of predicting the structure of a social network when the network itself is totally missing while some other information regarding the nodes is available. We propose a two-phase method based on the bootstrap probabilistic graph. The first phase generates an implicit social network under the form of a probabilistic graph. The second phase applies probabilistic graph-based measures to produce the final prediction. We assess our method empirically over a large data collection obtained from Flickr, using interest groups as the initial information. The experiments confirm the effectiveness of our approach. %@ 978-1-4503-0055-1

@inproceedings{Leroy:2010:CSL:1835804.1835855, abstract = {In the traditional link prediction problem, a snapshot of a social network is used as a starting point to predict, by means of graph-theoretic measures, the links that are likely to appear in the future. In this paper, we introduce cold start link prediction as the problem of predicting the structure of a social network when the network itself is totally missing while some other information regarding the nodes is available. We propose a two-phase method based on the bootstrap probabilistic graph. The first phase generates an implicit social network under the form of a probabilistic graph. The second phase applies probabilistic graph-based measures to produce the final prediction. We assess our method empirically over a large data collection obtained from Flickr, using interest groups as the initial information. The experiments confirm the effectiveness of our approach.}, acmid = {1835855}, added-at = {2014-04-24T15:04:54.000+0200}, address = {New York, NY, USA}, author = {Leroy, Vincent and Cambazoglu, B. Barla and Bonchi, Francesco}, biburl = {https://www.bibsonomy.org/bibtex/2075ddef91e76dac87ef6efe1547e15ce/b.helmerich}, booktitle = {Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, description = {Cold start link prediction}, doi = {10.1145/1835804.1835855}, interhash = {660d904a7cdd03a447d18dce03316c06}, intrahash = {075ddef91e76dac87ef6efe1547e15ce}, isbn = {978-1-4503-0055-1}, keywords = {thema:exploiting_place_features_in_link_prediction_on_location-based_social_networks}, location = {Washington, DC, USA}, numpages = {10}, pages = {393--402}, publisher = {ACM}, series = {KDD '10}, timestamp = {2014-04-24T15:04:54.000+0200}, title = {Cold Start Link Prediction}, url = {http://doi.acm.org/10.1145/1835804.1835855}, year = 2010 }