Joint Item Recommendation and Attribute Inference
- 25 July 2020
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
Abstract
In many recommender systems, users and items are associated with attributes, and users show preferences to items. The attribute information describes users'(items') characteristics and has a wide range of applications, such as user profiling, item annotation, and feature-enhanced recommendation. As annotating user (item) attributes is a labor intensive task, the attribute values are often incomplete with many missing attribute values. Therefore, item recommendation and attribute inference have become two main tasks in these platforms. Researchers have long converged that user(item) attributes and the preference behavior are highly correlated. Some researchers proposed to leverage one kind of data for the remaining task, and showed to improve performance. Nevertheless, these models either neglected the incompleteness of user~(item) attributes or regarded the correlation of the two tasks with simple models, leading to suboptimal performance of these two tasks. To this end, in this paper, we define these two tasks in an attributed user-item bipartite graph, and propose an Adaptive Graph Convolutional Network(AGCN) approach for joint item recommendation and attribute inference. The key idea of AGCN is to iteratively perform two parts: 1) Learning graph embedding parameters with previously learned approximated attribute values to facilitate two tasks; 2) Sending the approximated updated attribute values back to the attributed graph for better graph embedding learning. Therefore, AGCN could adaptively adjust the graph embedding learning parameters by incorporating both the given attributes and the estimated attribute values, in order to provide weakly supervised information to refine the two tasks. Extensive experimental results on three real-world datasets clearly show the effectiveness of the proposed model.Keywords
Funding Information
- National Natural Science Foundation of China (No.61725203, 61972125, U19A2079, 61722204, 61932009 and 61732008)
- National Key Research and Development Program of China (2017YFB0803301)
This publication has 26 references indexed in Scilit:
- Modeling the Evolution of Users’ Preferences and Social Links in Social Networking ServicesIEEE Transactions on Knowledge and Data Engineering, 2017
- Relevance Meets CoverageACM Transactions on Intelligent Systems and Technology, 2016
- The MovieLens DatasetsACM Transactions on Interactive Intelligent Systems, 2015
- Image-Based Recommendations on Styles and SubstitutesPublished by Association for Computing Machinery (ACM) ,2015
- Joint Link Prediction and Attribute Inference Using a Social-Attribute NetworkACM Transactions on Intelligent Systems and Technology, 2014
- Private traits and attributes are predictable from digital records of human behaviorProceedings of the National Academy of Sciences of the United States of America, 2013
- Factorization Machines with libFMACM Transactions on Intelligent Systems and Technology, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009
- Regression-based latent factor modelsPublished by Association for Computing Machinery (ACM) ,2009