{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:48:32Z","timestamp":1765889312144,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645605","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"3798-3809","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2664-6366","authenticated-orcid":false,"given":"Yunli","family":"Wang","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9502-5447","authenticated-orcid":false,"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-012X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8059-8528","authenticated-orcid":false,"given":"Shiyang","family":"Wen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9100-0964","authenticated-orcid":false,"given":"Dongying","family":"Kong","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9801-9292","authenticated-orcid":false,"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3636-3618","authenticated-orcid":false,"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Independent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Mathieu Blondel Olivier Teboul Quentin Berthet and Josip Djolonga. 2020. Fast Differentiable Sorting and Ranking. In ICML. 950--959."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Sebastian Bruch Masrour Zoghi Michael Bendersky and Marc Najork. 2019. Revisiting approximate metric optimization in the age of deep neural networks. In SIGIR. 1241--1244.","DOI":"10.1145\/3331184.3331347"},{"key":"e_1_3_2_2_3_1","volume-title":"From ranknet to lambdarank to lambdamart: An overview. Learning","author":"Burges Christopher JC","year":"2010","unstructured":"Christopher JC Burges. 2010. From ranknet to lambdarank to lambdamart: An overview. Learning (2010), 81."},{"key":"e_1_3_2_2_4_1","volume-title":"Hullender","author":"Burges Christopher J. C.","year":"2005","unstructured":"Christopher J. C. Burges, Tal Shaked, Erin Renshaw, Ari Lazier, Matt Deeds, Nicole Hamilton, and Gregory N. Hullender. 2005. Learning to rank using gradient descent. In ICML. 89--96."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Yunbo Cao Jun Xu Tie-Yan Liu Hang Li Yalou Huang and Hsiao-Wuen Hon. 2006. Adapting ranking SVM to document retrieval. In SIGIR. 186--193.","DOI":"10.1145\/1148170.1148205"},{"key":"e_1_3_2_2_6_1","unstructured":"Linzheng Chai Jian Yang Tao Sun Hongcheng Guo Jiaheng Liu Bing Wang Xiannian Liang Jiaqi Bai Tongliang Li Qiyao Peng et al. 2024. xCoT: Crosslingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning. arXiv preprint arXiv:2401.07037 (2024)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Ruey-Cheng Chen Luke Gallagher Roi Blanco and J. Shane Culpepper. 2017. Efficient Cost-Aware Cascade Ranking in Multi-Stage Retrieval. In SIGIR. 445-- 454.","DOI":"10.1145\/3077136.3080819"},{"key":"e_1_3_2_2_8_1","unstructured":"Zhao Chen Vijay Badrinarayanan Chen-Yu Lee and Andrew Rabinovich. 2018. GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks. In ICML. 793--802."},{"key":"e_1_3_2_2_9_1","unstructured":"Marco Cuturi Olivier Teboul and Jean-Philippe Vert. 2019. Differentiable Ranking and Sorting using Optimal Transport. In NeurIPS. 6858--6868."},{"key":"e_1_3_2_2_10_1","volume-title":"Salvatore Orlando, Raffaele Perego, Nicola Tonellotto, and Rossano Venturini.","author":"Dato Domenico","year":"2016","unstructured":"Domenico Dato, Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Nicola Tonellotto, and Rossano Venturini. 2016. Fast Ranking with Additive Ensembles of Oblivious and Non-Oblivious Regression Trees. ACM Trans. Inf. Syst. (2016), 15:1--15:31."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Luke Gallagher Ruey-Cheng Chen Roi Blanco and J. Shane Culpepper. 2019. Joint Optimization of Cascade Ranking Models. In WSDM. 15--23.","DOI":"10.1145\/3289600.3290986"},{"key":"e_1_3_2_2_12_1","unstructured":"Xavier Glorot Antoine Bordes and Yoshua Bengio. 2011. Deep Sparse Rectifier Neural Networks. In AISTATS. 315--323."},{"key":"e_1_3_2_2_13_1","unstructured":"Aditya Grover Eric Wang Aaron Zweig and Stefano Ermon. 2019. Stochastic Optimization of Sorting Networks via Continuous Relaxations. In ICLR."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Yuyao Guo Haoming Li Xiang Ao Min Lu Dapeng Liu Lei Xiao Jie Jiang and Qing He. 2022. Calibrated Conversion Rate Prediction via Knowledge Distillation under Delayed Feedback in Online Advertising. In CIKM. 3983--3987.","DOI":"10.1145\/3511808.3557557"},{"key":"e_1_3_2_2_15_1","volume-title":"Oren Sar Shalom, and Rita Osadchy","author":"Hadash Guy","year":"2018","unstructured":"Guy Hadash, Oren Sar Shalom, and Rita Osadchy. 2018. Rank and rate: multi-task learning for recommender systems. In RecSys. 451--454."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Yun He Xue Feng Cheng Cheng Geng Ji Yunsong Guo and James Caverlee. 2022. MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks. In WWW. 2205--2215.","DOI":"10.1145\/3485447.3512093"},{"key":"e_1_3_2_2_17_1","volume-title":"MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration. In WWW. 2236--2246.","author":"Huang Siguang","year":"2022","unstructured":"Siguang Huang, Yunli Wang, Lili Mou, Huayue Zhang, Han Zhu, Chuan Yu, and Bo Zheng. 2022. MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration. In WWW. 2236--2246."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Rolf Jagerman Zhen Qin Xuanhui Wang Michael Bendersky and Marc Najork. 2022. On Optimizing Top-K Metrics for Neural Ranking Models. In SIGIR. 2303--2307.","DOI":"10.1145\/3477495.3531849"},{"key":"e_1_3_2_2_19_1","volume-title":"DCAF: A Dynamic Computation Allocation Framework for Online Serving System. CoRR abs\/2006.09684","author":"Jiang Biye","year":"2020","unstructured":"Biye Jiang, Pengye Zhang, Rihan Chen, Binding Dai, Xinchen Luo, Yin Yang, Guan Wang, Guorui Zhou, Xiaoqiang Zhu, and Kun Gai. 2020. DCAF: A Dynamic Computation Allocation Framework for Online Serving System. CoRR abs\/2006.09684 (2020)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. In SIGKDD. 133--142.","DOI":"10.1145\/775047.775067"},{"key":"e_1_3_2_2_21_1","volume-title":"Brandon Houghton, Raul Sampedro, Peter Zhokhov, Bowen Baker, Adrien Ecoffet, Jie Tang, Oleg Klimov, and Jeff Clune.","author":"Kanitscheider Ingmar","year":"2021","unstructured":"Ingmar Kanitscheider, Joost Huizinga, David Farhi, William Hebgen Guss, Brandon Houghton, Raul Sampedro, Peter Zhokhov, Bowen Baker, Adrien Ecoffet, Jie Tang, Oleg Klimov, and Jeff Clune. 2021. Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft. CoRR abs\/2106.14876 (2021)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Alex Kendall Yarin Gal and Roberto Cipolla. 2018. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. In CVPR. 7482-- 7491.","DOI":"10.1109\/CVPR.2018.00781"},{"key":"e_1_3_2_2_23_1","unstructured":"G\u00fcnter Klambauer Thomas Unterthiner Andreas Mayr and Sepp Hochreiter. 2017. Self-Normalizing Neural Networks. In NeurIPS. 971--980."},{"key":"e_1_3_2_2_24_1","unstructured":"Ping Li Christopher J. C. Burges and Qiang Wu. 2007. McRank: Learning to Rank Using Multiple Classification and Gradient Boosting. In NeurIPS. 897--904."},{"key":"e_1_3_2_2_25_1","volume-title":"FAA: Fine-grained Attention Alignment for Cascade Document Ranking. In ACL. 1688--1700.","author":"Li Zhen","year":"2023","unstructured":"Zhen Li, Chongyang Tao, Jiazhan Feng, Tao Shen, Dongyan Zhao, Xiubo Geng, and Daxin Jiang. 2023. FAA: Fine-grained Attention Alignment for Cascade Document Ranking. In ACL. 1688--1700."},{"key":"e_1_3_2_2_26_1","volume-title":"mCL-NER: Cross-Lingual Named Entity Recognition via Multiview Contrastive Learning. arXiv preprint arXiv:2308.09073","author":"Mo Ying","year":"2023","unstructured":"Ying Mo, Jian Yang, Jiahao Liu, Qifan Wang, Ruoyu Chen, Jingang Wang, and Zhoujun Li. 2023. mCL-NER: Cross-Lingual Named Entity Recognition via Multiview Contrastive Learning. arXiv preprint arXiv:2308.09073 (2023)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Rama Kumar Pasumarthi Sebastian Bruch Xuanhui Wang Cheng Li Michael Bendersky Marc Najork Jan Pfeifer Nadav Golbandi Rohan Anil and Stephan Wolf. 2019. TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank. In KDD. ACM 2970--2978.","DOI":"10.1145\/3292500.3330677"},{"key":"e_1_3_2_2_28_1","unstructured":"Felix Petersen Christian Borgelt Hilde Kuehne and Oliver Deussen. 2021. Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision. In ICML. 8546--8555."},{"key":"e_1_3_2_2_29_1","unstructured":"Felix Petersen Christian Borgelt Hilde Kuehne and Oliver Deussen. 2022. Monotonic Differentiable Sorting Networks. In ICLR."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Jiarui Qin Jiachen Zhu Bo Chen Zhirong Liu Weiwen Liu Ruiming Tang Rui Zhang Yong Yu and Weinan Zhang. 2022. RankFlow: Joint Optimization of Multi-Stage Cascade Ranking Systems as Flows. In SIGIR. 814--824.","DOI":"10.1145\/3477495.3532050"},{"key":"e_1_3_2_2_31_1","volume-title":"CoRR abs\/1306.2597","author":"Qin Tao","year":"2013","unstructured":"Tao Qin and Tie-Yan Liu. 2013. Introducing LETOR 4.0 Datasets. CoRR abs\/1306.2597 (2013). arXiv:1306.2597 http:\/\/arxiv.org\/abs\/1306.2597"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9124-x"},{"key":"e_1_3_2_2_33_1","volume-title":"Xuanhui Wang, Michael Bendersky, and Marc Najork.","author":"Qin Zhen","year":"2021","unstructured":"Zhen Qin, Le Yan, Honglei Zhuang, Yi Tay, Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, and Marc Najork. 2021. Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?. In ICLR."},{"key":"e_1_3_2_2_34_1","unstructured":"Robin M. E. Swezey Aditya Grover Bruno Charron and Stefano Ermon. 2021. PiRank: Scalable Learning To Rank via Differentiable Sorting. In NeurIPS. 21644-- 21654."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Hongyan Tang Junning Liu Ming Zhao and Xudong Gong. 2020. Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations. In RecSys. 269--278.","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Michael J. Taylor John Guiver Stephen Robertson and Tom Minka. 2008. Soft- Rank: optimizing non-smooth rank metrics. In WSDM. 77--86.","DOI":"10.1145\/1341531.1341544"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Lidan Wang Jimmy Lin and Donald Metzler. 2011. A cascade ranking model for efficient ranked retrieval. In SIGIR. 105--114.","DOI":"10.1145\/2009916.2009934"},{"key":"e_1_3_2_2_38_1","volume-title":"Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking. CoRR abs\/2307.11096","author":"Wang Xuewei","year":"2023","unstructured":"Xuewei Wang, Qiang Jin, Shengyu Huang, Min Zhang, Xi Liu, Zhengli Zhao, Yukun Chen, Zhengyu Zhang, Jiyan Yang, EllieWen, Sagar Chordia,Wenlin Chen, and Qin Huang. 2023. Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking. CoRR abs\/2307.11096 (2023)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"XuanhuiWang Cheng Li Nadav Golbandi Michael Bendersky and Marc Najork. 2018. The LambdaLoss Framework for Ranking Metric Optimization. In CIKM. 1313--1322.","DOI":"10.1145\/3269206.3271784"},{"key":"e_1_3_2_2_40_1","unstructured":"YiningWang LiweiWang Yuanzhi Li Di He and Tie-Yan Liu. 2013. A Theoretical Analysis of NDCG Type Ranking Measures. In COLT. 25--54."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Yunli Wang Yu Wu Lili Mou Zhoujun Li and Wen-Han Chao. 2020. Formality Style Transfer with Shared Latent Space. In COLING. 2236--2249.","DOI":"10.18653\/v1\/2020.coling-main.203"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Mingrui Wu Yi Chang Zhaohui Zheng and Hongyuan Zha. 2009. Smoothing DCG for learning to rank: a novel approach using smoothed hinge functions. In CIKM. 1923--1926.","DOI":"10.1145\/1645953.1646266"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Jun Xu and Hang Li. 2007. AdaRank: a boosting algorithm for information retrieval. In SIGIR. 391--398.","DOI":"10.1145\/1277741.1277809"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Jian Yang Shuming Ma Li Dong Shaohan Huang Haoyang Huang Yuwei Yin Dongdong Zhang Liqun Yang FuruWei and Zhoujun Li. 2023. GanLM: Encoder- Decoder Pre-training with an Auxiliary Discriminator. In ACL. 9394--9412.","DOI":"10.18653\/v1\/2023.acl-long.522"},{"key":"e_1_3_2_2_45_1","unstructured":"Jian Yang Shuming Ma Haoyang Huang Dongdong Zhang Li Dong Shaohan Huang Alexandre Muzio Saksham Singhal Hany Hassan Xia Song and Furu Wei. 2021. Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task. In WMT. 446--455."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Jian Yang Shuming Ma Dongdong Zhang ShuangzhiWu Zhoujun Li and Ming Zhou. 2020. Alternating language modeling for cross-lingual pre-training. In AAAI. 9386--9393.","DOI":"10.1609\/aaai.v34i05.6480"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Jian Yang Yuwei Yin Shuming Ma Dongdong Zhang Zhoujun Li and Furu Wei. 2022. High-resource Language-specific Training for Multilingual Neural Machine Translation. In IJCAI. 4461--4467.","DOI":"10.24963\/ijcai.2022\/619"},{"key":"e_1_3_2_2_48_1","first-page":"1489","article-title":"GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation","volume":"31","author":"Yang Jian","year":"2023","unstructured":"Jian Yang, Yuwei Yin, Liqun Yang, Shuming Ma, Haoyang Huang, Dongdong Zhang, Furu Wei, and Zhoujun Li. 2023. GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation. TASLP 31 (2023), 1489--1498.","journal-title":"TASLP"},{"key":"e_1_3_2_2_49_1","volume-title":"Computation Resource Allocation Solution in Recommender Systems. CoRR abs\/2103.02259","author":"Yang Xun","year":"2021","unstructured":"Xun Yang, YunliWang, Cheng Chen, Qing Tan, Chuan Yu, Jian Xu, and Xiaoqiang Zhu. 2021. Computation Resource Allocation Solution in Recommender Systems. CoRR abs\/2103.02259 (2021)."},{"key":"e_1_3_2_2_50_1","volume-title":"NeurIPS","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient Surgery for Multi-Task Learning. In NeurIPS 2020."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Weixia Zhang Guangtao Zhai Ying Wei Xiaokang Yang and Kede Ma. 2023. Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective. In CVPR. 14071--14081.","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_2_52_1","unstructured":"Zhaohui Zheng Hongyuan Zha Tong Zhang Olivier Chapelle Keke Chen and Gordon Sun. 2007. A General Boosting Method and its Application to Learning Ranking Functions for Web Search. In NeurIPS. 1697--1704."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Singapore Singapore","acronym":"WWW '24"},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645605","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:31:59Z","timestamp":1755822719000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645605"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":52,"alternative-id":["10.1145\/3589334.3645605","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645605","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}