Learning Multiple Graphs for Document Recommendations

@inproceedings{citeulike:2774250, abstract = {The Web offers rich relational data with different semantics. In this paper, we address the problem of document recommendation in a digital library, where the documents in question are networked by citations and are associated with other entities by various relations. Due to the sparsity of a single graph and noise in graph construction, we propose a new method for combining multiple graphs to measure document similarities, where different factorization strategies are used based on the nature of different graphs. In particular, the new method seeks a single low-dimensional embedding of documents that captures their relative similarities in a latent space. Based on the obtained embedding, a new recommendation framework is developed using semi-supervised learning on graphs. In addition, we address the scalability issue and propose an incremental algorithm. The new incremental method significantly improves the efficiency by calculating the embedding for new incoming documents only. The new batch and incremental methods are evaluated on two real world datasets prepared from CiteSeer. Experiments demonstrate significant quality improvement for our batch method and significant efficiency improvement with tolerable quality loss for our incremental method.}, author = {Zhou, Ding and Zhu, Shenghuo and Yu, Kai and Song, Xiaodan and Tseng, Belle L. and Zha, Hongyuan and Giles(, Lee C. }, booktitle = {WWW2008}, citeulike-article-id = {2774250}, keywords = {graph, learning, machine-learning, network, recommendation}, month = {April}, posted-at = {2008-05-09 05:14:41}, priority = {2}, title = {Learning Multiple Graphs for Document Recommendations}, url = {http://www2008.org/papers/fp085.html}, year = {2008} }

TY - CONF ID - citeulike:2774250 L3 - citeulike-article-id:2774250 TI - Learning Multiple Graphs for Document Recommendations T2 - WWW2008 N2 - The Web offers rich relational data with different semantics. In this paper, we address the problem of document recommendation in a digital library, where the documents in question are networked by citations and are associated with other entities by various relations. Due to the sparsity of a single graph and noise in graph construction, we propose a new method for combining multiple graphs to measure document similarities, where different factorization strategies are used based on the nature of different graphs. In particular, the new method seeks a single low-dimensional embedding of documents that captures their relative similarities in a latent space. Based on the obtained embedding, a new recommendation framework is developed using semi-supervised learning on graphs. In addition, we address the scalability issue and propose an incremental algorithm. The new incremental method significantly improves the efficiency by calculating the embedding for new incoming documents only. The new batch and incremental methods are evaluated on two real world datasets prepared from CiteSeer. Experiments demonstrate significant quality improvement for our batch method and significant efficiency improvement with tolerable quality loss for our incremental method. KW - graph KW - learning KW - machine-learning KW - network KW - recommendation AU - Zhou, Ding AU - Zhu, Shenghuo AU - Yu, Kai AU - Song, Xiaodan AU - Tseng, Belle AU - Zha, Hongyuan AU - Giles(, Lee PY - 2008/04/21/ UR - http://www2008.org/papers/fp085.html ER -