Hierarchical Probabilistic Matrix Factorization with Network Topology for Multi-relational Social Network

Haoli Bai, Zenglin Xu, Bin Liu, Yingming Li
Proceedings of The 8th Asian Conference on Machine Learning, PMLR 63:270-285, 2016.

Abstract

Link prediction in multi-relational social networks has attracted much attention. For instance, we may care the chance of two users being friends based on their contacts of other patterns, e.g., SMS and phone calls. In previous work, matrix factorization models are typically applied in single-relational networks; however, two challenges arise to extend it into multi-relational networks. First, the interaction of different relation types is hard to be captured. The second is the cold start problem, as the prediction of new entities in multi-relational networks becomes even more challenging. In this article we propose a novel method called Hierarchical Probabilistic Matrix Factorization with Network Topology (HPMFNT). Our model exploits the network topology by extending the Katz index into multi-relational settings, which could efficiently model the multidimensional interplay via the auxiliary information from other relationships. We also utilize the extended Katz index along with entitiy attributes to solve the cold-start problem. Experiments on two real world datasets have shown that our model outperforms the state-of-the-art with a significant margin.

Cite this Paper

BibTeX
@InProceedings{pmlr-v63-bai103, title = {Hierarchical Probabilistic Matrix Factorization with Network Topology for Multi-relational Social Network}, author = {Bai, Haoli and Xu, Zenglin and Liu, Bin and Li, Yingming}, booktitle = {Proceedings of The 8th Asian Conference on Machine Learning}, pages = {270--285}, year = {2016}, editor = {Durrant, Robert J. and Kim, Kee-Eung}, 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/bai103.pdf}, url = {https://proceedings.mlr.press/v63/bai103.html}, abstract = {Link prediction in multi-relational social networks has attracted much attention. For instance, we may care the chance of two users being friends based on their contacts of other patterns, e.g., SMS and phone calls. In previous work, matrix factorization models are typically applied in single-relational networks; however, two challenges arise to extend it into multi-relational networks. First, the interaction of different relation types is hard to be captured. The second is the cold start problem, as the prediction of new entities in multi-relational networks becomes even more challenging. In this article we propose a novel method called Hierarchical Probabilistic Matrix Factorization with Network Topology (HPMFNT). Our model exploits the network topology by extending the Katz index into multi-relational settings, which could efficiently model the multidimensional interplay via the auxiliary information from other relationships. We also utilize the extended Katz index along with entitiy attributes to solve the cold-start problem. Experiments on two real world datasets have shown that our model outperforms the state-of-the-art with a significant margin.} }
Endnote
%0 Conference Paper %T Hierarchical Probabilistic Matrix Factorization with Network Topology for Multi-relational Social Network %A Haoli Bai %A Zenglin Xu %A Bin Liu %A Yingming 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-bai103 %I PMLR %P 270--285 %U https://proceedings.mlr.press/v63/bai103.html %V 63 %X Link prediction in multi-relational social networks has attracted much attention. For instance, we may care the chance of two users being friends based on their contacts of other patterns, e.g., SMS and phone calls. In previous work, matrix factorization models are typically applied in single-relational networks; however, two challenges arise to extend it into multi-relational networks. First, the interaction of different relation types is hard to be captured. The second is the cold start problem, as the prediction of new entities in multi-relational networks becomes even more challenging. In this article we propose a novel method called Hierarchical Probabilistic Matrix Factorization with Network Topology (HPMFNT). Our model exploits the network topology by extending the Katz index into multi-relational settings, which could efficiently model the multidimensional interplay via the auxiliary information from other relationships. We also utilize the extended Katz index along with entitiy attributes to solve the cold-start problem. Experiments on two real world datasets have shown that our model outperforms the state-of-the-art with a significant margin.
RIS
TY - CPAPER TI - Hierarchical Probabilistic Matrix Factorization with Network Topology for Multi-relational Social Network AU - Haoli Bai AU - Zenglin Xu AU - Bin Liu AU - Yingming Li BT - Proceedings of The 8th Asian Conference on Machine Learning DA - 2016/11/20 ED - Robert J. Durrant ED - Kee-Eung Kim ID - pmlr-v63-bai103 PB - PMLR DP - Proceedings of Machine Learning Research VL - 63 SP - 270 EP - 285 L1 - http://proceedings.mlr.press/v63/bai103.pdf UR - https://proceedings.mlr.press/v63/bai103.html AB - Link prediction in multi-relational social networks has attracted much attention. For instance, we may care the chance of two users being friends based on their contacts of other patterns, e.g., SMS and phone calls. In previous work, matrix factorization models are typically applied in single-relational networks; however, two challenges arise to extend it into multi-relational networks. First, the interaction of different relation types is hard to be captured. The second is the cold start problem, as the prediction of new entities in multi-relational networks becomes even more challenging. In this article we propose a novel method called Hierarchical Probabilistic Matrix Factorization with Network Topology (HPMFNT). Our model exploits the network topology by extending the Katz index into multi-relational settings, which could efficiently model the multidimensional interplay via the auxiliary information from other relationships. We also utilize the extended Katz index along with entitiy attributes to solve the cold-start problem. Experiments on two real world datasets have shown that our model outperforms the state-of-the-art with a significant margin. ER -
APA
Bai, H., Xu, Z., Liu, B. & Li, Y.. (2016). Hierarchical Probabilistic Matrix Factorization with Network Topology for Multi-relational Social Network. Proceedings of The 8th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 63:270-285 Available from https://proceedings.mlr.press/v63/bai103.html.

Related Material