Aentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Aention
نویسندگان
چکیده
Multimedia content is dominating today’s Web information. e nature of multimedia user-item interactions is 1/0 binary implicit feedback (e.g., photo likes, video views, song downloads, etc.), which can be collected at a larger scale with a much lower cost than explicit feedback (e.g., product ratings). However, the majority of existing collaborative ltering (CF) systems are not well-designed for multimedia recommendation, since they ignore the implicitness in users’ interactions with multimedia content. We argue that, in multimedia recommendation, there exists itemand component-level implicitness which blurs the underlying users’ preferences. e item-level implicitness means that users’ preferences on items (e.g., photos, videos, songs, etc.) are unknown, while the componentlevel implicitness means that inside each item users’ preferences on dierent components (e.g., regions in an image, frames of a video, etc.) are unknown. For example, a “view” on a video does not provide any specic information about how the user likes the video (i.e., item-level) and which parts of the video the user is interested in (i.e., component-level). In this paper, we introduce a novel aention mechanism in CF to address the challenging itemand component-level implicit feedback in multimedia recommendation, dubbed Aentive Collaborative Filtering (ACF). Specically, our aention model is a neural network that consists of two aention modules: the component-level aention module, starting from any content feature extraction network (e.g., CNN for images/videos), which learns to select informative components of multimedia items, and the item-level aention module, which learns to score the item preferences. ACF can be seamlessly incorporated into classic CF models with implicit feedback, such as BPR and SVD++, and eciently trained using SGD. rough extensive experiments on two real-world multimedia Web services: Vine and Pinterest, we show that ACF signicantly outperforms state-of-the-art CF methods. ∗Xiangnan He is the corresponding author. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for prot or commercial advantage and that copies bear this notice and the full citation on the rst page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permied. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specic permission and/or a fee. Request permissions from [email protected]. SIGIR’17, August 7–11, 2017, Shinjuku, Tokyo, Japan. © 2017 ACM. 978-1-4503-5022-8/17/08. . .$15.00 DOI: hp://dx.doi.org/10.1145/3077136.3080797 CCS CONCEPTS •Information systems →Multimedia information systems;
منابع مشابه
A New Similarity Measure Based on Item Proximity and Closeness for Collaborative Filtering Recommendation
Recommender systems utilize information retrieval and machine learning techniques for filtering information and can predict whether a user would like an unseen item. User similarity measurement plays an important role in collaborative filtering based recommender systems. In order to improve accuracy of traditional user based collaborative filtering techniques under new user cold-start problem a...
متن کاملUse of Semantic Similarity and Web Usage Mining to Alleviate the Drawbacks of User-Based Collaborative Filtering Recommender Systems
One of the most famous methods for recommendation is user-based Collaborative Filtering (CF). This system compares active user’s items rating with historical rating records of other users to find similar users and recommending items which seems interesting to these similar users and have not been rated by the active user. As a way of computing recommendations, the ultimate goal of the user-ba...
متن کاملQoS-based Web Service Recommendation using Popular-dependent Collaborative Filtering
Since, most of the organizations present their services electronically, the number of functionally-equivalent web services is increasing as well as the number of users that employ those web services. Consequently, plenty of information is generated by the users and the web services that lead to the users be in trouble in finding their appropriate web services. Therefore, it is required to provi...
متن کاملIntelligent Approach for Attracting Churning Customers in Banking Industry Based on Collaborative Filtering
During the last years, increased competition among banks has caused many developments in banking experiences and technology, while leading to even more churning customers due to their desire of having the best services. Therefore, it is an extremely significant issue for the banks to identify churning customers and attract them to the banking system again. In order to tackle this issue, this pa...
متن کاملPersonalized Book Recommendation Based on Ontology and Collaborative Filtering Algorithm
Information recommendation service is one of important functions of digital library, aiming at the problem that book recommendation service exists the insufficient requirement mining of service object information in the current university library, personalized book recommendation method based on ontology information and collaborative filtering algorithm (abbreviated as OI-CFA algorithm) is prop...
متن کامل