{"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/attentional-factorization-machines-learning","title":"Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks","arxiv_id":"1708.04617","date":"2017-08-15","proceeding":null,"authors":["Jun Xiao","Hao Ye","Xiangnan He","Hanwang Zhang","Fei Wu","Tat-Seng Chua"],"abstract":"Factorization Machines (FMs) are a supervised learning approach that enhances\nthe linear regression model by incorporating the second-order feature\ninteractions. Despite effectiveness, FM can be hindered by its modelling of all\nfeature interactions with the same weight, as not all feature interactions are\nequally useful and predictive. For example, the interactions with useless\nfeatures may even introduce noises and adversely degrade the performance. In\nthis work, we improve FM by discriminating the importance of different feature\ninteractions. We propose a novel model named Attentional Factorization Machine\n(AFM), which learns the importance of each feature interaction from data via a\nneural attention network. Extensive experiments on two real-world datasets\ndemonstrate the effectiveness of AFM. Empirically, it is shown on regression\ntask AFM betters FM with a $8.6\\%$ relative improvement, and consistently\noutperforms the state-of-the-art deep learning methods Wide&Deep and DeepCross\nwith a much simpler structure and fewer model parameters. Our implementation of\nAFM is publicly available at:\nhttps://github.com/hexiangnan/attentional_factorization_machine","url_abs":"http://arxiv.org/abs/1708.04617v1","url_pdf":"http://arxiv.org/pdf/1708.04617v1.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":"attentional-factorization-machines-learning","repo_url":"https://github.com/hexiangnan/attentional_factorization_machine","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attentional-factorization-machines-learning","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":"attentional-factorization-machines-learning","repo_url":"https://github.com/hzn666/rlbid_ea","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attentional-factorization-machines-learning","repo_url":"https://github.com/MindSpore-scientific-2/code-12/tree/main/factorized-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"attentional-factorization-machines-learning","repo_url":"https://github.com/shenweichen/DeepCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"attentional-factorization-machines-learning","repo_url":"https://github.com/shenweichen/DeepCTR-Torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"attentional-factorization-machines-learning","repo_url":"https://github.com/tangxyw/RecAlgorithm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"attentional-factorization-machines-learning","repo_url":"https://github.com/xue-pai/FuxiCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"linear-regression","method_name":"Linear Regression"},{"method_slug":"wide-deep","method_name":"Wide&Deep"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.04617","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}