Abstract
Sequential recommendations have attracted increasing attention from both academia and industry in recent years. They predict a given user’s next choice of items by mainly modeling the sequential relations over a sequence of the user’s interactions with the items. However, most of the existing sequential recommendation algorithms mainly focus on the sequential dependencies between item IDs within sequences, while ignoring the rich and complex relations embedded in the auxiliary information, such as items’ image information and textual information. Such complex relations can help us better understand users’ preferences towards items, and thus benefit from the recommendations. To bridge this gap, we propose an auxiliary information-enhanced sequential recommendation algorithm called memory fusion network for recommendation (MFN4Rec) to incorporate both items’ image and textual information for sequential recommendations. Accordingly, item IDs, item image information and item textual information are regarded as three modalities. By comprehensively modelling the sequential relations within modalities and interaction relations across modalities, MFN4Rec can learn a more informative representation of users’ preferences for more accurate recommendations. Extensive experiments on two real-world datasets demonstrate the superiority of MFN4Rec over state-of-the-art sequential recommendation algorithms.
Highlights
Recommender systems have had an ever-increasingly important role in our daily life to help users effectively and efficiently find the items of their interest from a large amount of choices
To bridge the aforementioned drawbacks of existing works, in this paper, we aim at developing an accurate sequential recommendation algorithm by effectively extracting and aggregating useful information from multi-modal auxiliary information, as well as modeling the complex interaction relations embedded in them
A more effective and reliable algorithm which can effectively incorporate different types of auxiliary information for sequential recommendations is in need, which motivates our work in this paper
Summary
Recommender systems have had an ever-increasingly important role in our daily life to help users effectively and efficiently find the items of their interest from a large amount of choices. The final hidden state of the RNN is regarded as the user’s preference for generating recommendations Effective, such a method mainly considers the interaction relations across different modalities, while the sequential dependencies within each modality are weakened. To bridge the aforementioned drawbacks of existing works, in this paper, we aim at developing an accurate sequential recommendation algorithm by effectively extracting and aggregating useful information from multi-modal auxiliary information, as well as modeling the complex interaction relations embedded in them. We devise a memory fusion network for recommendation (MFN4Rec) by effectively integrating the relevant information from three modalities, i.e., item IDs, item images and item description texts, and modelling the complex relations between and within modalities. A multi-view gated memory network (MGMN) is devised to effectively model the complex interaction relations across different modalities. The results have demonstrated the superiority of our proposed SRS algorithm over the state-of-the-art ones when performing sequential recommendations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
