{"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/package-recommendation-with-intra-and-inter","title":"Package Recommendation with Intra- and Inter-Package Attention Networks","arxiv_id":null,"date":"2021-07-11","proceeding":"SIGIR 2021 7","authors":["Chen Li","Yuanfu Lu","Wei Wang"],"abstract":"With the booming of online social networks in the mobile internet,\r\nan emerging recommendation scenario has played a vital role in\r\ninformation acquisition for user, where users are no longer recommended with a single item or item list, but a combination of\r\nheterogeneous and diverse objects (called a package, e.g., a package\r\nincluding news, publisher, and friends viewing the news). Different\r\nfrom the conventional recommendation where users are recommended with the item itself, in package recommendation, users\r\nwould show great interests on the explicitly displayed objects that\r\ncould have a significant influence on the user behaviors. However,\r\nto the best of our knowledge, few effort has been made for package recommendation and existing approaches can hardly model\r\nthe complex interactions of diverse objects in a package. Thus, in\r\nthis paper, we make a first study on package recommendation and\r\npropose an Intra- and inter-package attention network for Package Recommendation (IPRec). Specifically, for package modeling,\r\nan intra-package attention network is put forward to capture the\r\nobject-level intention of user interacting with the package, while\r\nan inter-package attention network acts as a package-level information encoder that captures collaborative features of neighboring packages. In addition, to capture users preference representation,\r\nwe present a user preference learner equipped with a fine-grained\r\nfeature aggregation network and coarse-grained package aggregation network. Extensive experiments on three real-world datasets\r\ndemonstrate that IPRec significantly outperforms the state of the\r\narts. Moreover, the model analysis demonstrates the interpretability\r\nof our IPRec and the characteristics of user behaviors. Codes and\r\ndatasets can be obtained at https://github.com/LeeChenChen/IPRec.","url_abs":"http://nlp.csai.tsinghua.edu.cn/~xrb/publications/SIGIR-21_IPRec.pdf","url_pdf":"http://nlp.csai.tsinghua.edu.cn/~xrb/publications/SIGIR-21_IPRec.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":[{"paper_slug":"package-recommendation-with-intra-and-inter","repo_url":"https://github.com/LeeChenChen/IPRec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"package-recommendation-with-intra-and-inter","repo_url":"https://github.com/PaddlePaddle/PaddleRec/tree/master/models/rank/iprec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"package-recommendation-with-intra-and-inter","repo_url":"https://github.com/renmada/PaddleRec/tree/iprec/models/rank/iprec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}