{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T14:21:32Z","timestamp":1784557292589,"version":"3.55.0"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["92470205"],"award-info":[{"award-number":["92470205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Major Science and Technology","award":["Z251100008425002"],"award-info":[{"award-number":["Z251100008425002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:p>\n                    <jats:bold>Click-through rate (CTR)<\/jats:bold>\n                    prediction holds a pivotal role in online advertising and recommendation systems, where even small improvements can significantly boost revenue. Existing research primarily focuses on designing dual-stream architectures to capture effective complex feature interactions from both explicit and implicit perspectives. However, these approaches are faced with two major challenges: (1) the high complexity of feature interaction learning, which increases computational demands and the overfitting risk, and (2) the imbalance between explicit and implicit modules, where one module\u2019s output may dominate the final prediction. To address these issues, in this article, we propose\n                    <jats:bold>dual-stream multi-layer perceptron (DS-MLP)<\/jats:bold>\n                    , a novel feature interaction framework for the CTR prediction task. Specially, it leverages knowledge distillation to consolidate the capacity of learning explicit feature interaction into a main MLP network, while a parallel MLP simultaneously captures implicit feature interactions as a complement. To effectively optimize the DS-MLP architecture, we further design a specific learning approach with two alignment strategies for enhancing the compatibility of the two MLP components. Experiments demonstrate that\n                    <jats:italic toggle=\"yes\">DS-MLP<\/jats:italic>\n                    , though merely a vanilla MLP structure (the final model), can achieve state-of-the-art performance across three widely used benchmarks, offering a scalable and efficient solution for large-scale recommendation systems. Our code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/RUCAIBox\/DS-MLP\">https:\/\/github.com\/RUCAIBox\/DS-MLP<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3819238","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T13:31:37Z","timestamp":1779975097000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Stream MLP Is All You Need for CTR Prediction"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8557-5437","authenticated-orcid":false,"given":"Kesha","family":"Ou","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5569-2591","authenticated-orcid":false,"given":"Zhen","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8333-6196","authenticated-orcid":false,"given":"Wayne Xin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4769-5030","authenticated-orcid":false,"given":"Long","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7186-4960","authenticated-orcid":false,"given":"Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"29","author":"Blondel Mathieu","year":"2016","unstructured":"Mathieu Blondel, Akinori Fujino, Naonori Ueda, and Masakazu Ishihata. 2016. Higher-order factorization machines. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 29."},{"key":"e_1_3_2_3_2","unstructured":"Andreas Buja Werner Stuetzle and Yi Shen. 2005. Loss Functions for Binary Class Probability Estimation and Classification: Structure and Applications. Working Draft 13."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457321"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481915"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5768"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"e_1_3_2_9_2","unstructured":"Jiaxin Deng Shiyao Wang Kuo Cai Lejian Ren Qigen Hu Weifeng Ding Qiang Luo and Guorui Zhou. 2025. OneRec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv:2502.18965. Retrieved from https:\/\/arxiv.org\/abs\/2502.18965"},{"key":"e_1_3_2_10_2","first-page":"1675","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Du Simon","year":"2019","unstructured":"Simon Du, Jason Lee, Haochuan Li, Liwei Wang, and Xiyu Zhai. 2019. Gradient descent finds global minima of deep neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 1675\u20131685."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367359"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Lin Guan Jia Qi Yang Zhishan Zhao Beichuan Zhang Bo Sun Xuanyuan Luo Jinan Ni Xiaowen Li Yuhang Qi Zhifang Fan et al. 2025. Make it long keep it fast: End-to-end 10k-sequence modeling at billion scale on Douyin. arXiv:2511.06077. Retrieved from https:\/\/arxiv.org\/abs\/2511.06077","DOI":"10.1145\/3774904.3792811"},{"key":"e_1_3_2_13_2","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A factorization-machine based neural network for CTR prediction. arXiv:1703.04247. Retrieved from https:\/\/arxiv.org\/abs\/1703.04247"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467384"},{"key":"e_1_3_2_15_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/70405.70408"},{"key":"e_1_3_2_17_2","unstructured":"Bojian Hou Xiaolong Liu Xiaoyi Liu Jiaqi Xu Yasmine Badr Mengyue Hang Sudhanshu Chanpuriya Junqing Zhou Yuhang Yang Han Xu et al. 2026. Kunlun: Establishing scaling laws for massive-scale recommendation systems through unified architecture design. arXiv:2602.10016. Retrieved from https:\/\/arxiv.org\/abs\/2602.10016"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347043"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_20_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv:2001.08361. Retrieved from https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411912"},{"key":"e_1_3_2_22_2","unstructured":"Lingwei Kong Lu Wang Changping Peng Zhangang Lin Ching Law and Jingping Shao. 2025. Generative click-through rate prediction with applications to search advertising. arXiv:2507.11246. Retrieved from https:\/\/arxiv.org\/abs\/2507.11246"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748046"},{"key":"e_1_3_2_24_2","unstructured":"Honghao Li Yiwen Zhang Yi Zhang Hanwei Li Lei Sang and Jieming Zhu. 2024. FCN: Fusing exponential and linear cross network for click-through rate prediction. arXiv:2407.13349. Retrieved from https:\/\/arxiv.org\/abs\/2407.13349"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357951"},{"key":"e_1_3_2_26_2","unstructured":"Zekun Li Shu Wu Zeyu Cui and Xiaoyu Zhang. 2021. GraphFM: Graph factorization machines for feature interaction modeling. arXiv:2105.11866. Retrieved from https:\/\/arxiv.org\/abs\/2105.11866"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313497"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1466-8238.2007.00358.x"},{"key":"e_1_3_2_30_2","first-page":"3139","volume-title":"Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence","author":"Lu Wantong","year":"2021","unstructured":"Wantong Lu, Yantao Yu, Yongzhe Chang, Zhen Wang, Chenhui Li, and Bo Yuan. 2021. A dual input-aware factorization machine for CTR prediction. In Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence, 3139\u20133145."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25577"},{"key":"e_1_3_2_32_2","unstructured":"Kesha Ou Zhen Tian Wayne Xin Zhao Hongyu Lu and Ji-Rong Wen. 2026. GenCI: Generative modeling of user interest shift via cohort-based intent learning for CTR prediction. arXiv:2601.18251. Retrieved from https:\/\/arxiv.org\/abs\/2601.18251"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186040"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002919"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/1639537.1639542"},{"key":"e_1_3_2_36_2","first-page":"1149","volume-title":"Proceedings of the IEEE International Conference on Data Mining","author":"Qu Y.","year":"2017","unstructured":"Y. Qu, H. Cai, W. Zhang, Y. Wen, and J. Wang. 2017. Product-based neural networks for user response prediction. In Proceedings of the IEEE International Conference on Data Mining. IEEE, 1149\u20131154."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3233770"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0452"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"e_1_3_2_41_2","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for thin deep nets. In Proceedings of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014886"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449930"},{"key":"e_1_3_2_45_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)","author":"Tan Xu","year":"2019","unstructured":"Xu Tan, Yi Ren, Di He, Tao Qin, Zhou Zhao, and Tie-Yan Liu. 2019. Multilingual neural machine translation with knowledge distillation. In Proceedings of the 7th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570384"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591681"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671740"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615089"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531970"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729956"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_54_2","unstructured":"Zhiqiang Wang Qingyun She and Junlin Zhang. 2021. MaskNet: Introducing feature-wise multiplication to CTR ranking models by instance-guided mask. arXiv:2102.07619. Retrieved from https:\/\/arxiv.org\/abs\/2102.07619"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/435"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/545"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403309"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"e_1_3_2_59_2","first-page":"1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (ICML)","author":"Yin Mingjia","year":"2025","unstructured":"Mingjia Yin, Junwei Pan, Hao Wang, Ximei Wang, Shangyu Zhang, Jie Jiang, Defu Lian, and Enhong Chen. 2025. From feature interaction to feature generation: A generative paradigm of CTR prediction models. In Proceedings of the 42nd International Conference on Machine Learning (ICML), Vol. 267. PMLR, 1\u201323."},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412077"},{"key":"e_1_3_2_61_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Zagoruyko Sergey","year":"2017","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2017. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"e_1_3_2_62_2","unstructured":"Buyun Zhang Liang Luo Yuxin Chen Jade Nie Xi Liu Daifeng Guo Yanli Zhao Shen Li Yuchen Hao Yantao Yao et al. 2024. Wukong: Towards a scaling law for large-scale recommendation. arXiv:2403.02545. Retrieved from https:\/\/arxiv.org\/abs\/2403.02545"},{"key":"e_1_3_2_63_2","unstructured":"Moyu Zhang Yun Chen Yujun Jin Jinxin Hu and Yu Zhang. 2025. DGenCTR: Towards a universal generative paradigm for click-through rate prediction via discrete diffusion. arXiv:2508.14500. Retrieved from https:\/\/arxiv.org\/abs\/2508.14500"},{"key":"e_1_3_2_64_2","unstructured":"Pengyu Zhao Kecheng Xiao Yuanxing Zhang Kaigui Bian and Wei Yan. 2020. AMEIR: Automatic behavior modeling and interaction exploration in recommender system. arXiv:2006.05933. Retrieved from https:\/\/arxiv.org\/abs\/2006.05933"},{"key":"e_1_3_2_65_2","article-title":"Rocket launching: A universal and efficient framework for training well-performing light net","volume":"32","author":"Zhou Guorui","year":"2018","unstructured":"Guorui Zhou, Ying Fan, Runpeng Cui, Weijie Bian, Xiaoqiang Zhu, and Kun Gai. 2018. Rocket launching: A universal and efficient framework for training well-performing light net. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_67_2","first-page":"3389","volume-title":"IEEE Transactions on Knowledge and Data Engineering","volume":"35","author":"Zhu Chenxu","year":"2021","unstructured":"Chenxu Zhu, Bo Chen, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, and Yong Yu. 2021. AIM: Automatic interaction machine for click-through rate prediction. IEEE Transactions on Knowledge and Data Engineering 35, 4 (2021), 3389\u20133403."},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761507"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591988"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412704"},{"key":"e_1_3_2_71_2","unstructured":"Difan Zou Yuan Cao Dongruo Zhou and Quanquan Gu. 2018. Stochastic gradient descent optimizes over-parameterized deep ReLU networks. arXiv:1811.08888. Retrieved from https:\/\/arxiv.org\/abs\/1811.08888"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3819238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:59:51Z","timestamp":1784555991000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3819238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":70,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3819238"],"URL":"https:\/\/doi.org\/10.1145\/3819238","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"assertion":[{"value":"2025-09-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}