Multi-Order Attentive Ranking Model for Sequential Recommendation

Abstract

In modern e-commerce, the temporal order behind users’ transactions implies the importance of exploiting the transition dependency among items for better inferring what a user prefers to interact in “near future”. The types of interaction among items are usually divided into individual-level interaction that can stand out the transition order between a pair of items, or union-level relation between a set of items and single one. However, most of existing work only captures one of them from a single view, especially on modeling the individual-level interaction. In this paper, we propose a Multi-order Attentive Ranking Model (MARank) to unify both individual- and union-level item interaction into preference inference model from multiple views. The idea is to represent user’s short-term preference by embedding user himself and a set of present items into multi-order features from intermedia hidden status of a deep neural network. With the help of attention mechanism, we can obtain a unified embedding to keep the individual-level interactions with a linear combination of mapped items’ features. Then, we feed the aggregated embedding to a designed residual neural network to capture union-level interaction. Thorough experiments are conducted to show the features of MARank under various component settings. Furthermore experimental results on several public datasets show that MARank significantly outperforms the state-of-the-art baselines on different evaluation metrics. The source code can be found at https://github.com/voladorlu/MARank.

Joint Relational Dependency Learning for Sequential Recommendation

“…However, the model in [15] suffers from data sparsity problems. Therefore, in order to solve the sparsity problem when merely modeling collective dependencies, Yu et al [19] add individual (i.e. individual-level) dependencies into collective (i.e.…”

“…We conduct experiments to validate JDR-L for Top-N sequential recommendation task on the real-world dataset, i.e., Movie&TV dataset [19], that belongs to Amazon data 1 . Since the original datasets are sparse, we firstly filter out users with fewer than 10 interactions as in [19]. The statistical information of the before-processing and after-processing of Movie&TV dataset is shown in Table 1.…”

“…The statistical information of the before-processing and after-processing of Movie&TV dataset is shown in Table 1. Following the evaluation settings in [19], we set train/test with ratios 80/20. We compare JRD-L with three baselines: BPR-MF [12] is a widely used matrix factorization method for sequential RS; TranRec [4] models users as translation vectors operating on item sequences for sequential RS); RNN-based model (i.e., GRU4Rec [6] uses basic Gated Recurrent Unit for sequential RS); FPMC [13] is a typical Markov chain method modeling individiual item interactions; Multi-level item temporal dependency model (MARank) [19] models both individual-level and union-level interactions with factorization model.…”

“…1(b). Therefore, individual-level dependencies can capture individual influence between a pair of single item, but may neglect the collective influence [19] among three or more items denoted by union-level dependencies, as shown in Fig. 1(c).…”

“…Namely, the collective influence is caused by the dependency of a group of items on a single item. To alleviate this issue, Yu et al [19] leverages both individual and collective influence for better sequential recommendation performance. However, two main drawbacks exist in this methods: 1) the information of individual and collective influence is simply added to the output proximity score of a factorization-based model, leveraging none of the long-term information; 2) The union-level interaction requires a group of items to be joint modeled within a limit length of sequence, which may lead to sparsity problem.…”