{"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/gated-attentive-autoencoder-for-content-aware","title":"Gated Attentive-Autoencoder for Content-Aware Recommendation","arxiv_id":"1812.02869","date":"2018-12-07","proceeding":null,"authors":["Chen Ma","Peng Kang","Bin Wu","Qinglong Wang","Xue Liu"],"abstract":"The rapid growth of Internet services and mobile devices provides an\nexcellent opportunity to satisfy the strong demand for the personalized item or\nproduct recommendation. However, with the tremendous increase of users and\nitems, personalized recommender systems still face several challenging\nproblems: (1) the hardness of exploiting sparse implicit feedback; (2) the\ndifficulty of combining heterogeneous data. To cope with these challenges, we\npropose a gated attentive-autoencoder (GATE) model, which is capable of\nlearning fused hidden representations of items' contents and binary ratings,\nthrough a neural gating structure. Based on the fused representations, our\nmodel exploits neighboring relations between items to help infer users'\npreferences. In particular, a word-level and a neighbor-level attention module\nare integrated with the autoencoder. The word-level attention learns the item\nhidden representations from items' word sequences, while favoring informative\nwords by assigning larger attention weights. The neighbor-level attention\nlearns the hidden representation of an item's neighborhood by considering its\nneighbors in a weighted manner. We extensively evaluate our model with several\nstate-of-the-art methods and different validation metrics on four real-world\ndatasets. The experimental results not only demonstrate the effectiveness of\nour model on top-N recommendation but also provide interpretable results\nattributed to the attention modules.","url_abs":"http://arxiv.org/abs/1812.02869v1","url_pdf":"http://arxiv.org/pdf/1812.02869v1.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":"gated-attentive-autoencoder-for-content-aware","repo_url":"https://github.com/allenjack/GATE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"product-recommendation","task_name":"Product Recommendation"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.02869","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}