{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:40:56Z","timestamp":1759970456440,"version":"build-2065373602"},"reference-count":38,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"],"award-info":[{"award-number":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"]}]},{"name":"Anhui Natural Science Foundation","award":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"],"award-info":[{"award-number":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"]}]},{"name":"Anhui Provincial University Excellent Talent Support Program Key Projects","award":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"],"award-info":[{"award-number":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"]}]},{"name":"Major Natural Science Research Project of Anhui Provincial Universities","award":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"],"award-info":[{"award-number":["62001004","2008085MF218","gxyqZD2021124","2024AH040039"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The click-through rate (CTR) forecast is among the mainstream research directions in the domain of recommender systems, especially in online advertising suggestions. Among them, the multilayer perceptron (MLP) has been extensively utilized as the cornerstone of deep CTR prediction models. However, current neural network-based CTR prediction models commonly employ a single MLP network to capture nonlinear interactions between high-order features, while disregarding the interaction among differentiated features, resulting in poor model performance. Although studies such as DeepFM have proposed dual-branch interaction models to learn complex features, they still fall short of achieving more nuanced feature fusion. To address these challenges, we propose a novel model, the Deep Double Towers model (DDT), which improves the accuracy of CTR prediction through multi-head bilinear fusion while incorporating symmetry in its architecture. Specifically, the DDT model leverages symmetric parallel MLP networks to capture the interactions between differentiated features in a more structured and balanced manner. Furthermore, the multi-head bilinear fusion layer enables refined feature fusion through symmetry-aware operations, ensuring that feature interactions are aligned and symmetrically integrated. Experimental results on publicly available datasets, such as Criteo and Avazu, show that DDT surpasses existing models in improving the accuracy of CTR prediction, with symmetry contributing to more effective and balanced feature fusion.<\/jats:p>","DOI":"10.3390\/sym17020159","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T05:50:53Z","timestamp":1737525053000},"page":"159","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Double Towers Click Through Rate Prediction Model with Multi-Head Bilinear Fusion"],"prefix":"10.3390","volume":"17","author":[{"given":"Yuan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230601, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0009-7281","authenticated-orcid":false,"given":"Xiaobao","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230601, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230601, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230601, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"0925","DOI":"10.1016\/j.neucom.2022.01.035","article-title":"Multi-scale and multi-channel neural network for click-through rate prediction","volume":"480","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_2","first-page":"156","article-title":"Deep match to rank model for personalized click-through rate prediction","volume":"34","author":"Lyu","year":"2020","journal-title":"AAAI Tech. Track AI Web"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102853","DOI":"10.1016\/j.ipm.2021.102853","article-title":"Click-through rate prediction in online advertising: A literature review","volume":"59","author":"Yang","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"110704","DOI":"10.1016\/j.knosys.2023.110704","article-title":"A knowledge distillation-based deep interaction compressed network for CTR prediction","volume":"275","author":"Guan","year":"2023","journal-title":"Knowl. -Based Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.ins.2022.08.009","article-title":"Click-through rate prediction using transfer learning with fifine-tuned parameters","volume":"612","author":"Yang","year":"2022","journal-title":"Inform. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.neucom.2021.05.103","article-title":"An introduction to deep learning in natural language processing: Models, tech-niques, and tools","volume":"470","author":"Lauriola","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"6233","DOI":"10.1007\/s00500-022-07149-x","article-title":"Exploring Different Interaction Among Features For CTR Prediction","volume":"26","author":"Yang","year":"2022","journal-title":"Soft Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.procs.2021.02.116","article-title":"Explicit sparse self-attentive network for CTR prediction","volume":"183","author":"Luo","year":"2021","journal-title":"Procedia Comput. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1016\/j.ins.2020.09.005","article-title":"Multi-view feature transfer for click-through rate prediction","volume":"546","author":"Jiang","year":"2021","journal-title":"Inform. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.ins.2022.04.050","article-title":"DRIN: Deep Recurrent Interaction Network for click-through rate prediction","volume":"604","author":"Jun","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_11","first-page":"1725","article-title":"DeepFM: A factorization-machine based neural network for CTR prediction","volume":"521","author":"Guo","year":"2017","journal-title":"Int. Jt. Conf. Artif. Intell."},{"key":"ref_12","first-page":"12","article-title":"Deep & Cross Network for Ad Click Predictions","volume":"604","author":"Wang","year":"2017","journal-title":"Assoc. Comput. Mach."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xiao, J., Ye, H., He, X., Zhang, H., Wu, F., and Chua, T.-S. (2017, January 19\u201325). Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia.","DOI":"10.24963\/ijcai.2017\/435"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"102076","DOI":"10.1016\/j.ipm.2019.102076","article-title":"HoAFM: A High-order Attentive Factorization Machine for CTR Pre-diction","volume":"57","author":"Tao","year":"2020","journal-title":"Inf. Process. Manag."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rendle, S. (2010, January 13\u201317). Factorization Machines. Proceedings of the IEEE International Conference on Data Mining, Sydney, Australia.","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1016\/j.ins.2015.03.069","article-title":"Discovering predictors of mental health service utilization with k-support regularized logistic regression","volume":"329","author":"Sidahmed","year":"2016","journal-title":"Inf. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shan, Y., Hoens, T.R., Jiao, J., Wang, H., Yu, D., and Mao, J.C. (2016, January 13\u201317). Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939704"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.ins.2021.06.079","article-title":"Deep Field Relation Neural Network for click-through rate prediction","volume":"577","author":"Zou","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Huang, T., Zhang, Z., and Zhang, J. (2019, January 16\u201320). FiBiNET: Combining Feature Importance and Bilinear Feature Interaction for Click-through Rate Prediction. Proceedings of the Thirteenth ACM Conference on Recommender Systems, Copenhagen, Denmark.","DOI":"10.1145\/3298689.3347043"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103589","DOI":"10.1016\/j.artint.2021.103589","article-title":"Bayesian feature interaction selection for factorization machines","volume":"302","author":"Chen","year":"2022","journal-title":"Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3306","DOI":"10.1109\/TII.2020.3036164","article-title":"Deep Dynamic Interest Learning With Session Local and Global Consistency for Click-Through Rate Predictions","volume":"18","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4552","DOI":"10.1609\/aaai.v37i4.25577","article-title":"FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction","volume":"37","author":"Mao","year":"2023","journal-title":"AAAI"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"106767","DOI":"10.1016\/j.knosys.2021.106767","article-title":"Coarse-to-fine: A dual-view attention network for click-through rate predic-tion","volume":"216","author":"Song","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Juan, Y., Zhuang, Y., Chin, W.S., and Lin, C. (2016, January 15\u201319). Field-aware factorization machines for CTR prediction. Proceedings of the Tenth ACM Conference on Recommender Systems, Boston, MA, USA.","DOI":"10.1145\/2959100.2959134"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103072","DOI":"10.1016\/j.ipm.2022.103072","article-title":"A multiview graph collaborative filtering by incorporating homogeneous and heterogeneous signals","volume":"59","author":"Zheng","year":"2021","journal-title":"Inf. Process. Manag."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.neucom.2021.02.036","article-title":"A joint learning model for click-through prediction in display advertising","volume":"445","author":"Liu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhu, C., Li, G., Zhang, W., Lai, J., Tang, R., He, X., Li, Z., and Yu, Y. (2020, January 6\u201310). AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction. Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event.","DOI":"10.1145\/3394486.3403314"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., and Shah, H. (2016, January 15). Wide & Deep Learning for Recommender Systems. Proceedings of the DLRS 2016: Workshop on Deep Learning for Recommender Systems, Boston, MA, USA.","DOI":"10.1145\/2988450.2988454"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, B., Xue, N., Guo, H., Tang, R., Zafeiriou, S., He, X., and Li, Z. (2020, January 25\u201330). AutoGroup: Automatic Feature Grouping for modeling Explicit High-Order Feature Interactions in CTR Prediction. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.","DOI":"10.1145\/3397271.3401082"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, X., and Chua, T.-S. (2017, January 7\u201311). Neural Factorization Machines for Sparse Predictive Analytics. Proceedings of the SIGIR\u201917, Tokyo, Japan.","DOI":"10.1145\/3077136.3080777"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"109135","DOI":"10.1016\/j.knosys.2022.109135","article-title":"ICE-DEN: A click-through rate prediction method based on interest contribution extraction of dynamic attention intensity","volume":"250","author":"Jing","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_32","unstructured":"Bian, W., Wu, K., Ren, L., Pi, Q., Zhang, Y., Xiao, C., Sheng, X.R., Zhu, Y.N., Chan, Z., and Mou, N. (2022, January 21\u201325). CAN: Feature Co-Action Network for Click-Through Rate Prediction. Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"126441","DOI":"10.1016\/j.neucom.2023.126441","article-title":"A survey of graph neural network based recommendation in social networks","volume":"549","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neucom.2021.10.049","article-title":"Adapted transformer network for news recommendation","volume":"469","author":"Huang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_35","unstructured":"Wang, Z., She, Q., and Zhang, J. (2021). MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by In-stance-Guided Mask. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, F., Gu, H., Li, D., Lu, T., Zhang, P., and Gu, N. (2023, January 21\u201325). Towards deeper, lighter and interpretable cross network for ctr prediction. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, Birmingham, UK.","DOI":"10.1145\/3583780.3615089"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Tian, Z., Bai, T., Zhao, W.X., Wen, J.R., and Cao, Z. (2023, January 23\u201327). EulerNet: Adaptive Feature Interaction Learning via Euler\u2019s Formula for CTR Prediction. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Taiwan, China.","DOI":"10.1145\/3539618.3591681"},{"key":"ref_38","first-page":"3609","article-title":"Adaptive factorization network: Learning adaptive-order feature interactions","volume":"34","author":"Cheng","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/2\/159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:33:30Z","timestamp":1759919610000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/2\/159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,22]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["sym17020159"],"URL":"https:\/\/doi.org\/10.3390\/sym17020159","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,1,22]]}}}