%0 Generic %1 liu2016multibehavioral %A Liu, Qiang %A Wu, Shu %A Wang, Liang %D 2016 %K collaborative_filtering deep_learning recurrent_neural_network %T Multi-behavioral Sequential Prediction with Recurrent Log-bilinear Model %U http://arxiv.org/abs/1608.07102 %X With the rapid growth of Internet applications, sequential prediction in collaborative filtering has become an emerging and crucial task. Given the behavioral history of a specific user, predicting his or her next choice plays a key role in improving various online services. Meanwhile, there are more and more scenarios with multiple types of behaviors, while existing works mainly study sequences with a single type of behavior. As a widely used approach, Markov chain based models are based on a strong independence assumption. As two classical neural network methods for modeling sequences, recurrent neural networks can not well model short-term contexts, and the log-bilinear model is not suitable for long-term contexts. In this paper, we propose a Recurrent Log-BiLinear (RLBL) model. It can model multiple types of behaviors in historical sequences with behavior-specific transition matrices. RLBL applies a recurrent structure for modeling long-term contexts. It models several items in each hidden layer and employs position-specific transition matrices for modeling short-term contexts. Moreover, considering continuous time difference in behavioral history is a key factor for dynamic prediction, we further extend RLBL and replace position-specific transition matrices with time-specific transition matrices, and accordingly propose a Time-Aware Recurrent Log-BiLinear (TA-RLBL) model. Experimental results show that the proposed RLBL model and TA-RLBL model yield significant improvements over the competitive compared methods on three datasets, i.e., Movielens-1M dataset, Global Terrorism Database and Tmall dataset with different numbers of behavior types.

@misc{liu2016multibehavioral, abstract = {With the rapid growth of Internet applications, sequential prediction in collaborative filtering has become an emerging and crucial task. Given the behavioral history of a specific user, predicting his or her next choice plays a key role in improving various online services. Meanwhile, there are more and more scenarios with multiple types of behaviors, while existing works mainly study sequences with a single type of behavior. As a widely used approach, Markov chain based models are based on a strong independence assumption. As two classical neural network methods for modeling sequences, recurrent neural networks can not well model short-term contexts, and the log-bilinear model is not suitable for long-term contexts. In this paper, we propose a Recurrent Log-BiLinear (RLBL) model. It can model multiple types of behaviors in historical sequences with behavior-specific transition matrices. RLBL applies a recurrent structure for modeling long-term contexts. It models several items in each hidden layer and employs position-specific transition matrices for modeling short-term contexts. Moreover, considering continuous time difference in behavioral history is a key factor for dynamic prediction, we further extend RLBL and replace position-specific transition matrices with time-specific transition matrices, and accordingly propose a Time-Aware Recurrent Log-BiLinear (TA-RLBL) model. Experimental results show that the proposed RLBL model and TA-RLBL model yield significant improvements over the competitive compared methods on three datasets, i.e., Movielens-1M dataset, Global Terrorism Database and Tmall dataset with different numbers of behavior types.}, added-at = {2017-01-16T14:05:48.000+0100}, author = {Liu, Qiang and Wu, Shu and Wang, Liang}, biburl = {https://www.bibsonomy.org/bibtex/2376a5a3d3fd46f31a12ac8dc84f68216/dallmann}, description = {Multi-behavioral Sequential Prediction with Recurrent Log-bilinear Model}, interhash = {7eae58b3a02e1cdafd6d6af3f1f9dbc1}, intrahash = {376a5a3d3fd46f31a12ac8dc84f68216}, keywords = {collaborative_filtering deep_learning recurrent_neural_network}, note = {cite arxiv:1608.07102Comment: IEEE Transactions on Knowledge and Data Engineering (TKDE), under review}, timestamp = {2017-01-16T14:05:48.000+0100}, title = {Multi-behavioral Sequential Prediction with Recurrent Log-bilinear Model}, url = {http://arxiv.org/abs/1608.07102}, year = 2016 }