{"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/190412579","title":"Operation-aware Neural Networks for User Response Prediction","arxiv_id":"1904.12579","date":"2019-04-02","proceeding":null,"authors":["Yi Yang","Baile Xu","Furao Shen","Jian Zhao"],"abstract":"User response prediction makes a crucial contribution to the rapid\ndevelopment of online advertising system and recommendation system. The\nimportance of learning feature interactions has been emphasized by many works.\nMany deep models are proposed to automatically learn high-order feature\ninteractions. Since most features in advertising system and recommendation\nsystem are high-dimensional sparse features, deep models usually learn a\nlow-dimensional distributed representation for each feature in the bottom\nlayer. Besides traditional fully-connected architectures, some new operations,\nsuch as convolutional operations and product operations, are proposed to learn\nfeature interactions better. In these models, the representation is shared\namong different operations. However, the best representation for different\noperations may be different. In this paper, we propose a new neural model named\nOperation-aware Neural Networks (ONN) which learns different representations\nfor different operations. Our experimental results on two large-scale\nreal-world ad click/conversion datasets demonstrate that ONN consistently\noutperforms the state-of-the-art models in both offline-training environment\nand online-training environment.","url_abs":"http://arxiv.org/abs/1904.12579v1","url_pdf":"http://arxiv.org/pdf/1904.12579v1.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":"190412579","repo_url":"https://github.com/UlionTse/mlgb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"190412579","repo_url":"https://github.com/shenweichen/DeepCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"190412579","repo_url":"https://github.com/shenweichen/DeepCTR-Torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"190412579","repo_url":"https://github.com/xue-pai/FuxiCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.12579","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}