{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/item-silk-road-recommending-items-from","title":"Item Silk Road: Recommending Items from Information Domains to Social Users","arxiv_id":"1706.03205","date":"2017-06-10","proceeding":null,"authors":["Xiang Wang","Xiangnan He","Liqiang Nie","Tat-Seng Chua"],"abstract":"Online platforms can be divided into information-oriented and social-oriented\ndomains. The former refers to forums or E-commerce sites that emphasize\nuser-item interactions, like Trip.com and Amazon; whereas the latter refers to\nsocial networking services (SNSs) that have rich user-user connections, such as\nFacebook and Twitter. Despite their heterogeneity, these two domains can be\nbridged by a few overlapping users, dubbed as bridge users. In this work, we\naddress the problem of cross-domain social recommendation, i.e., recommending\nrelevant items of information domains to potential users of social networks. To\nour knowledge, this is a new problem that has rarely been studied before.\n  Existing cross-domain recommender systems are unsuitable for this task since\nthey have either focused on homogeneous information domains or assumed that\nusers are fully overlapped. Towards this end, we present a novel Neural Social\nCollaborative Ranking (NSCR) approach, which seamlessly sews up the user-item\ninteractions in information domains and user-user connections in SNSs. In the\ninformation domain part, the attributes of users and items are leveraged to\nstrengthen the embedding learning of users and items. In the SNS part, the\nembeddings of bridge users are propagated to learn the embeddings of other\nnon-bridge users. Extensive experiments on two real-world datasets demonstrate\nthe effectiveness and rationality of our NSCR method.","url_abs":"http://arxiv.org/abs/1706.03205v1","url_pdf":"http://arxiv.org/pdf/1706.03205v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"collaborative-ranking","task_name":"Collaborative Ranking"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/recommendation-systems-on-epinions","task":"Recommendation Systems","dataset":"Epinions","model":"NSCR (Wang et al., 2017)","rank_in_archive_order":2,"of":4,"metrics":{"MAE":"0.8044","RMSE":"1.0425"},"uses_additional_data":false},{"leaderboard":"/sota/recommendation-systems-on-wechat","task":"Recommendation Systems","dataset":"WeChat","model":"NSCR (Wang et al., 2017)","rank_in_archive_order":2,"of":2,"metrics":{"AUC":"0.7727","P@10":"0.0736"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.03205","atlas_url":"https://app.syntology.ai/?focus=1706.03205","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}