Abstract
Image recommendation plays an important role for exploring user potential interests in large-scale image sharing websites (e.g., Flickr and Instagram). Social relationships have been exploited to learn user preference, and shown their effectiveness. We argue that their performance improvement tends to be limited, as most existing approaches only consider the side of social influence from friends to a user. However, social influence is reciprocal per se as the preference of friends will be also influenced by the user herself. In this paper, we propose a deep neural network for image recommendation (dubbed RSIM) by leveraging reciprocal social influence, and optimize the preferences of users and friends simultaneously. Specifically, we split images into three types: positive image by an active user, social image by her social friends, and negative image by neither of them. We contend that a user prefers positive image to social image, which is in turn better than negative image for relative preference learning. Two neural networks are designed to capture user and image representations by tags and visual features, respectively. The proposed model is evaluated on a real dataset crawled from Flickr. The experimental results show that better performance can be reached than the state-of-the-art social image recommendation models in terms of precision.
Highlights
Photo sharing has become an important interactive manner for active users to build and retain social connections or relationships with like-minded users in some social applications, such as Flickr1 and Instagram.2 due to the large volume of shared pictures, it has been becoming more and more challenging to locate images of interest, which is wellknown as the issue of information overload
RELATED WORK we provide a brief overview about related research in image recommendation and social recommender systems
EXPERIMENTS we mainly aim to investigate whether our proposed RSIM model can obtain satisfying performance in comparison with other counterparts for top-N image recommendation
Summary
Photo sharing has become an important interactive manner for active users to build and retain social connections or relationships with like-minded users in some social applications, such as Flickr and Instagram. due to the large volume of shared pictures, it has been becoming more and more challenging to locate images of interest, which is wellknown as the issue of information overload. Social recommenders often do not provide the incorporation of image contents As a result, these issues will limit the performance improvement of collaborative filtering and item recommendation to some extent. For social friend v, she will prefer positive image i1 to social image i3, both of which are ranked higher than negative image i− In this way, reciprocal social influence can be well modeled and help promote the learning of user preferences. We devise a deep neural model to realize the reciprocity of social influence for recommendations, and incorporate the visual contents of images to boost the representation of both users and items. The experimental results show that our approach obtain better performance than other counterparts in ranking accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
