{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:03:46Z","timestamp":1765357426743,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC grant","award":["62141220, 61972253, U1908212, 62172276, 61972254"],"award-info":[{"award-number":["62141220, 61972253, U1908212, 62172276, 61972254"]}]},{"name":"Open Research Projects of Zhejiang Lab","award":["No. 2022NL0AB01"],"award-info":[{"award-number":["No. 2022NL0AB01"]}]},{"name":"Shanghai Science and Technology Development Funds","award":["23YF1420500"],"award-info":[{"award-number":["23YF1420500"]}]},{"name":"National Key R&D Program of China","award":["No. 2021ZD0110303"],"award-info":[{"award-number":["No. 2021ZD0110303"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599935","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"4437-4448","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["S\n            <sup>2<\/sup>\n            phere: Semi-Supervised Pre-training for Web Search over Heterogeneous Learning to Rank Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3869-7881","authenticated-orcid":false,"given":"Yuchen","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5451-3253","authenticated-orcid":false,"given":"Haoyi","family":"Xiong","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9266-3044","authenticated-orcid":false,"given":"Linghe","family":"Kong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-8098","authenticated-orcid":false,"given":"Qingzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9212-1947","authenticated-orcid":false,"given":"Shuaiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6934-1685","authenticated-orcid":false,"given":"Guihai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209985"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341981.3344218"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331347"},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems","author":"Burges Christopher J. C.","year":"2006","unstructured":"Christopher J. C. Burges , Robert Ragno , and Quoc Viet Le . 2006 . Learning to Rank with Nonsmooth Cost Functions. In Advances in Neural Information Processing Systems 19 , Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems , Vancouver, British Columbia, Canada , December 4-7, 2006. 193--200. Christopher J. C. Burges, Robert Ragno, and Quoc Viet Le. 2006. Learning to Rank with Nonsmooth Cost Functions. In Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 4-7, 2006. 193--200."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the Yahoo! Learning to Rank Challenge, held at ICML (JMLR Proceedings","volume":"24","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Yi Chang . 2011 . Yahoo! Learning to Rank Challenge Overview . In Proceedings of the Yahoo! Learning to Rank Challenge, held at ICML (JMLR Proceedings , Vol. 14). JMLR.org, 1-- 24 . Olivier Chapelle and Yi Chang. 2011. Yahoo! Learning to Rank Challenge Overview. In Proceedings of the Yahoo! Learning to Rank Challenge, held at ICML (JMLR Proceedings, Vol. 14). JMLR.org, 1--24."},{"key":"e_1_3_2_2_7_1","volume-title":"Processing of the 36th Annual Conference on Neural Information Processing Systems.","author":"Chen Baixu","year":"2022","unstructured":"Baixu Chen , Junguang Jiang , Ximei Wang , Pengfei Wan , Jianmin Wang , and Mingsheng Long . 2022 . Debiased Self-Training for Semi-Supervised Learning . In Processing of the 36th Annual Conference on Neural Information Processing Systems. Baixu Chen, Junguang Jiang, Ximei Wang, Pengfei Wan, Jianmin Wang, and Mingsheng Long. 2022. Debiased Self-Training for Semi-Supervised Learning. In Processing of the 36th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2668120"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/133160.133199"},{"key":"e_1_3_2_2_11_1","volume-title":"Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems","author":"Dong Li","year":"2019","unstructured":"Li Dong , Nan Yang , Wenhui Wang , Furu Wei , Xiaodong Liu , Yu Wang , Jianfeng Gao , Ming Zhou , and Hsiao-Wuen Hon . 2019. Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems , Vol. 32 ( 2019 ). Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2019. Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.407"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130348.3130374"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775067"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150429"},{"key":"e_1_3_2_2_18_1","volume-title":"LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 3146--3154","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke , Qi Meng , Thomas Finley , Taifeng Wang , Wei Chen , Weidong Ma , Qiwei Ye , and Tie-Yan Liu . 2017 . LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 3146--3154 . Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 3146--3154."},{"volume-title":"Processing of the 2nd International Conference on Learning Representations.","author":"Diederik","key":"e_1_3_2_2_19_1","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes . In Processing of the 2nd International Conference on Learning Representations. Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In Processing of the 2nd International Conference on Learning Representations."},{"key":"e_1_3_2_2_20_1","unstructured":"Ping Li Qiang Wu and Christopher Burges. 2008. McRank: Learning to Rank Using Multiple Classification and Gradient Boosting. In Advances in Neural Information Processing Systems. 65--72.  Ping Li Qiang Wu and Christopher Burges. 2008. McRank: Learning to Rank Using Multiple Classification and Gradient Boosting. In Advances in Neural Information Processing Systems. 65--72."},{"key":"e_1_3_2_2_21_1","volume-title":"COLTR: Semi-supervised Learning to Rank with Co-training and Over-parameterization for Web Search","author":"Li Yuchen","year":"2023","unstructured":"Yuchen Li , Haoyi Xiong , Qingzhong Wang , Linghe Kong , Hao Liu , Haifang Li , Jiang Bian , Shuaiqiang Wang , Guihai Chen , Dejing Dou , 2023 . COLTR: Semi-supervised Learning to Rank with Co-training and Over-parameterization for Web Search . IEEE Transactions on Knowledge and Data Engineering ( 2023). Yuchen Li, Haoyi Xiong, Qingzhong Wang, Linghe Kong, Hao Liu, Haifang Li, Jiang Bian, Shuaiqiang Wang, Guihai Chen, Dejing Dou, et al. 2023. COLTR: Semi-supervised Learning to Rank with Co-training and Over-parameterization for Web Search. IEEE Transactions on Knowledge and Data Engineering (2023)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467146"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467149"},{"key":"e_1_3_2_2_24_1","volume-title":"Context-aware learning to rank with self-attention. arXiv preprint arXiv:2005.10084","author":"Pobrotyn Przemys\u0142aw","year":"2020","unstructured":"Przemys\u0142aw Pobrotyn , Tomasz Bartczak , Miko\u0142aj Synowiec , Rados\u0142aw Bia\u0142obrzeski , and Jaros\u0142aw Bojar . 2020. Context-aware learning to rank with self-attention. arXiv preprint arXiv:2005.10084 ( 2020 ). Przemys\u0142aw Pobrotyn, Tomasz Bartczak, Miko\u0142aj Synowiec, Rados\u0142aw Bia\u0142obrzeski, and Jaros\u0142aw Bojar. 2020. Context-aware learning to rank with self-attention. arXiv preprint arXiv:2005.10084 (2020)."},{"key":"e_1_3_2_2_25_1","volume-title":"Neuralndcg: Direct optimisation of a ranking metric via differentiable relaxation of sorting. arXiv preprint arXiv:2102.07831","author":"Pobrotyn Przemys\u0142aw","year":"2021","unstructured":"Przemys\u0142aw Pobrotyn and Rados\u0142aw Bia\u0142obrzeski . 2021 . Neuralndcg: Direct optimisation of a ranking metric via differentiable relaxation of sorting. arXiv preprint arXiv:2102.07831 (2021). Przemys\u0142aw Pobrotyn and Rados\u0142aw Bia\u0142obrzeski. 2021. Neuralndcg: Direct optimisation of a ranking metric via differentiable relaxation of sorting. arXiv preprint arXiv:2102.07831 (2021)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733078"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00195"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9124-x"},{"key":"e_1_3_2_2_29_1","volume-title":"arXiv preprint arXiv:1306.2597","author":"Qin Tao","year":"2013","unstructured":"Tao Qin and Tie-Yan Liu . 2013. Introducing LETOR 4.0 datasets. arXiv preprint arXiv:1306.2597 ( 2013 ). Tao Qin and Tie-Yan Liu. 2013. Introducing LETOR 4.0 datasets. arXiv preprint arXiv:1306.2597 (2013)."},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the 9th International Conference on Learning Representations, ICLR.","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 Proceedings of the 9th International Conference on Learning Representations, ICLR. 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 Proceedings of the 9th International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_2_31_1","volume-title":"Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence. In International Conference on Machine Learning, ICML 2022","volume":"18152","author":"Qiu Zi-Hao","year":"2022","unstructured":"Zi-Hao Qiu , Quanqi Hu , Yongjian Zhong , Lijun Zhang , and Tianbao Yang . 2022 . Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence. In International Conference on Machine Learning, ICML 2022 , 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research , Vol. 162). PMLR, 18122-- 18152 . Zi-Hao Qiu, Quanqi Hu, Yongjian Zhong, Lijun Zhang, and Tianbao Yang. 2022. Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 18122--18152."},{"key":"e_1_3_2_2_32_1","volume-title":"Ernie: Enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223","author":"Sun Yu","year":"2019","unstructured":"Yu Sun , Shuohuan Wang , Yukun Li , Shikun Feng , Xuyi Chen , Han Zhang , Xin Tian , Danxiang Zhu , Hao Tian , and Hua Wu . 2019 . Ernie: Enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223 (2019). Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, and Hua Wu. 2019. Ernie: Enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223 (2019)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063620"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341544"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.528"},{"key":"e_1_3_2_2_36_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017 . Attention is All you Need . In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 5998--6008 . Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953039"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390306"},{"key":"e_1_3_2_2_39_1","volume-title":"Algorithmic Foundation of Deep X-risk Optimization. arXiv preprint arXiv:2206.00439","author":"Yang Tianbao","year":"2022","unstructured":"Tianbao Yang . 2022. Algorithmic Foundation of Deep X-risk Optimization. arXiv preprint arXiv:2206.00439 ( 2022 ). Tianbao Yang. 2022. Algorithmic Foundation of Deep X-risk Optimization. arXiv preprint arXiv:2206.00439 (2022)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220219"},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of 5th international joint conference on natural language processing. 929--937","author":"Zhao Shiqi","year":"2011","unstructured":"Shiqi Zhao , Haifeng Wang , Chao Li , Ting Liu , and Yi Guan . 2011 . Automatically generating questions from queries for community-based question answering . In Proceedings of 5th international joint conference on natural language processing. 929--937 . Shiqi Zhao, Haifeng Wang, Chao Li, Ting Liu, and Yi Guan. 2011. Automatically generating questions from queries for community-based question answering. In Proceedings of 5th international joint conference on natural language processing. 929--937."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20907"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277792"},{"key":"e_1_3_2_2_44_1","unstructured":"Lixin Zou Haitao Mao Xiaokai Chu Jiliang Tang Wenwen Ye Shuaiqiang Wang and Dawei Yin. 2022. A Large Scale Search Dataset for Unbiased Learning to Rank. In NeurIPS.  Lixin Zou Haitao Mao Xiaokai Chu Jiliang Tang Wenwen Ye Shuaiqiang Wang and Dawei Yin. 2022. A Large Scale Search Dataset for Unbiased Learning to Rank. In NeurIPS."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467147"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Long Beach CA USA","acronym":"KDD '23"},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599935","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:42Z","timestamp":1750178262000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599935"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":45,"alternative-id":["10.1145\/3580305.3599935","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599935","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}