{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:30:33Z","timestamp":1785511833722,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"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":[[2021,8,14]]},"DOI":"10.1145\/3447548.3467223","type":"proceedings-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T06:12:05Z","timestamp":1628748725000},"page":"1812-1820","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Towards Robust Prediction on Tail Labels"],"prefix":"10.1145","author":[{"given":"Tong","family":"Wei","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Wei","family":"Tu","sequence":"additional","affiliation":[{"name":"4Paradigm Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Feng","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo-Ping","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 22nd International Conference on World Wide Web. Rio de Janeiro, Brazil, 13--24","author":"Agrawal R.","unstructured":"R. Agrawal , A. Gupta , Y. Prabhu , and M. Varma . 2013. Multi-label learning with millions of labels: Recommending advertiser bid phrases for web pages . In Proceedings of the 22nd International Conference on World Wide Web. Rio de Janeiro, Brazil, 13--24 . R. Agrawal, A. Gupta, Y. Prabhu, and M. Varma. 2013. Multi-label learning with millions of labels: Recommending advertiser bid phrases for web pages. In Proceedings of the 22nd International Conference on World Wide Web. Rio de Janeiro, Brazil, 13--24."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 10th ACM International Conference on Web Search and Data Mining","author":"Babbar R.","unstructured":"R. Babbar and B. Sch\u00f6lkopf . 2017. DiSMEC: Distributed sparse machines for extreme multi-label classification . In Proceedings of the 10th ACM International Conference on Web Search and Data Mining . Cambridge, UK, 721--729. R. Babbar and B. Sch\u00f6lkopf. 2017. DiSMEC: Distributed sparse machines for extreme multi-label classification. In Proceedings of the 10th ACM International Conference on Web Search and Data Mining. Cambridge, UK, 721--729."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05791-5"},{"key":"e_1_3_2_1_4_1","unstructured":"K. Bhatia H. Jain P. Kar M. Varma and P. Jain. 2015. Sparse local embeddings for extreme multi-label classification. In Advances in Neural Information Processing Systems. Montreal Canada 730--738.  K. Bhatia H. Jain P. Kar M. Varma and P. Jain. 2015. Sparse local embeddings for extreme multi-label classification. In Advances in Neural Information Processing Systems. Montreal Canada 730--738."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Bi W.","unstructured":"W. Bi and J. T. Kwok . 2013. Efficient multi-label classification with many labels . In Proceedings of the 30th International Conference on Machine Learning . Atlanta, GA, 405--413. W. Bi and J. T. Kwok. 2013. Efficient multi-label classification with many labels. In Proceedings of the 30th International Conference on Machine Learning. Atlanta, GA, 405--413."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chang W.-C.","year":"2020","unstructured":"W.-C. Chang , H.-F. Yu , K. Zhong , Y. Yang , and I. Dhillon . 2020. X-BERT: eXtreme Multi-label Text Classification with BERT . Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ( 2020 ). W.-C. Chang, H.-F. Yu, K. Zhong, Y. Yang, and I. Dhillon. 2020. X-BERT: eXtreme Multi-label Text Classification with BERT. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2020)."},{"key":"e_1_3_2_1_7_1","volume-title":"Advances in Neural Information Processing Systems.","author":"Chen Y.-N.","unstructured":"Y.-N. Chen and H.-T. Lin . 2012. Feature-aware label space dimension reduction for multi-label classification . In Advances in Neural Information Processing Systems. Lake Tahoe, NV , 1529--1537. Y.-N. Chen and H.-T. Lin. 2012. Feature-aware label space dimension reduction for multi-label classification. In Advances in Neural Information Processing Systems. Lake Tahoe, NV, 1529--1537."},{"key":"e_1_3_2_1_8_1","unstructured":"H. Daume III N. Karampatziakis J. Langford and P. Mineiro. 2016. Logarithmic time one-against-some. arXiv preprint arXiv:1606.04988 (2016).  H. Daume III N. Karampatziakis J. Langford and P. Mineiro. 2016. Logarithmic time one-against-some. arXiv preprint arXiv:1606.04988 (2016)."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","author":"Yen I. E.-H.","unstructured":"I. E.-H. Yen , X. Huang , P. Ravikumar , K. Zhong , and I. Dhillon . 2016. PD-Sparse: A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification . In Proceedings of The 33rd International Conference on Machine Learning . New York, NY, 3069--3077. I. E.-H. Yen, X. Huang, P. Ravikumar, K. Zhong, and I. Dhillon. 2016. PD-Sparse: A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification. In Proceedings of The 33rd International Conference on Machine Learning. New York, NY, 3069--3077."},{"key":"e_1_3_2_1_10_1","unstructured":"I. Evron E. Moroshko and K. Crammer. 2018. Efficient Loss-Based Decoding on Graphs for Extreme Classification. In Advances in Neural Information Processing Systems Montr\u00e9 al Canada. 7233--7244.  I. Evron E. Moroshko and K. Crammer. 2018. Efficient Loss-Based Decoding on Graphs for Extreme Classification. In Advances in Neural Information Processing Systems Montr\u00e9 al Canada. 7233--7244."},{"key":"e_1_3_2_1_11_1","unstructured":"C. Guo A. Mousavi X. Wu D. Holtmann-Rice S. Kale S. Reddi and S. Kumar. 2019. Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces. In Advances in Neural Information Processing Systems.  C. Guo A. Mousavi X. Wu D. Holtmann-Rice S. Kale S. Reddi and S. Kumar. 2019. Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Jain H.","unstructured":"H. Jain , Y. Prabhu , and M. Varma . 2016. Extreme multi-label loss functions for recommendation, tagging, ranking & other missing label applications .. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . San Francisco, CA, 935--944. H. Jain, Y. Prabhu, and M. Varma. 2016. Extreme multi-label loss functions for recommendation, tagging, ranking & other missing label applications.. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, CA, 935--944."},{"key":"e_1_3_2_1_13_1","unstructured":"D. Saini K. Dave H. Jain S. Agarwal M. Varma K. Dahiya A. Mittal. 2019. DeepXML: Scalable & Accurate Deep Extreme Classification for Matching User Queries to Advertiser Bid Phrases.  D. Saini K. Dave H. Jain S. Agarwal M. Varma K. Dahiya A. Mittal. 2019. DeepXML: Scalable & Accurate Deep Extreme Classification for Matching User Queries to Advertiser Bid Phrases."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kang B.","year":"2020","unstructured":"B. Kang , S. Xie , M. Rohrbach , Z. Yan , A. Gordo , J. Feng , and Y. Kalantidis . 2020. Decoupling representation and classifier for long-tailed recognition . Proceedings of the International Conference on Learning Representations ( 2020 ). B. Kang, S. Xie, M. Rohrbach, Z. Yan, A. Gordo, J. Feng, and Y. Kalantidis. 2020. Decoupling representation and classifier for long-tailed recognition. Proceedings of the International Conference on Learning Representations (2020)."},{"key":"e_1_3_2_1_15_1","unstructured":"S. Khandagale H. Xiao and R. Babbar. 2019. Bonsai-Diverse and Shallow Trees for Extreme Multi-label Classification. arXiv preprint arXiv:1904.08249 (2019).  S. Khandagale H. Xiao and R. Babbar. 2019. Bonsai-Diverse and Shallow Trees for Extreme Multi-label Classification. arXiv preprint arXiv:1904.08249 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"McAuley J.","unstructured":"J. McAuley , R. Pandey , and J. Leskovec . 2015. Inferring networks of substitutable and complementary products . In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . Sydney, Australia, 785--794. J. McAuley, R. Pandey, and J. Leskovec. 2015. Inferring networks of substitutable and complementary products. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Sydney, Australia, 785--794."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","author":"Niculescu-Mizil A.","unstructured":"A. Niculescu-Mizil and M. E. Abbasnejad . 2017. Label filters for large scale multi-label classification . In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics . Fort Lauderdale, FL, 1448--1457. A. Niculescu-Mizil and M. E. Abbasnejad. 2017. Label filters for large scale multi-label classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale, FL, 1448--1457."},{"key":"e_1_3_2_1_18_1","volume-title":"LSHTC: A benchmark for large-scale text classification. arXiv preprint arXiv:1503.08581","author":"Partalas I.","year":"2015","unstructured":"I. Partalas , A. Kosmopoulos , N. Baskiotis , T. Artieres , G. Paliouras , E. Gaussier , I. Androutsopoulos , M.-R. Amini , and P. Galinari . 2015 . LSHTC: A benchmark for large-scale text classification. arXiv preprint arXiv:1503.08581 (2015). I. Partalas, A. Kosmopoulos, N. Baskiotis, T. Artieres, G. Paliouras, E. Gaussier, I. Androutsopoulos, M.-R. Amini, and P. Galinari. 2015. LSHTC: A benchmark for large-scale text classification. arXiv preprint arXiv:1503.08581 (2015)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 2018 World Wide Web Conference","author":"Prabhu Y.","unstructured":"Y. Prabhu , A. Kag , S. Harsola , R. Agrawal , and M. Varma . 2018. Parabel: Partitioned Label Trees for Extreme Classification with Application to Dynamic Search Advertising . In Proceedings of the 2018 World Wide Web Conference ( Lyon,France) (WWW). 993--1002. Y. Prabhu, A. Kag, S. Harsola, R. Agrawal, and M. Varma. 2018. Parabel: Partitioned Label Trees for Extreme Classification with Application to Dynamic Search Advertising. In Proceedings of the 2018 World Wide Web Conference (Lyon,France) (WWW). 993--1002."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Prabhu Y.","unstructured":"Y. Prabhu and M. Varma . 2014. FastXML: A fast, accurate and stable tree-classifier for extreme multi-label learning . In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York, NY, 263--272. Y. Prabhu and M. Varma. 2014. FastXML: A fast, accurate and stable tree-classifier for extreme multi-label learning. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, 263--272."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning. Stockholmsm\"a ssan, Stockholm Sweden, 4664--4673","author":"Siblini W.","unstructured":"W. Siblini , P. Kuntz , and F. Meyer . 2018. CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning . In Proceedings of the 35th International Conference on Machine Learning. Stockholmsm\"a ssan, Stockholm Sweden, 4664--4673 . W. Siblini, P. Kuntz, and F. Meyer. 2018. CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning. In Proceedings of the 35th International Conference on Machine Learning. Stockholmsm\"a ssan, Stockholm Sweden, 4664--4673."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097987"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00320"},{"key":"e_1_3_2_1_24_1","volume-title":"European Conference on Machine Learning","author":"Tsoumakas G.","unstructured":"G. Tsoumakas and I. Vlahavas . 2007. Random k-labelsets: An ensemble method for multilabel classification . In European Conference on Machine Learning . Warsaw, Poland, 406--417. G. Tsoumakas and I. Vlahavas. 2007. Random k-labelsets: An ensemble method for multilabel classification. In European Conference on Machine Learning. Warsaw, Poland, 406--417."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304889.3305056"},{"key":"e_1_3_2_1_26_1","volume-title":"Learning Compact Model for Large-Scale Multi-Label Data. In The 33rd AAAI Conference on Artificial Intelligence. 5385--5392","author":"Wei T.","year":"2019","unstructured":"T. Wei and Y.-F. Li . 2019 . Learning Compact Model for Large-Scale Multi-Label Data. In The 33rd AAAI Conference on Artificial Intelligence. 5385--5392 . T. Wei and Y.-F. Li. 2019. Learning Compact Model for Large-Scale Multi-Label Data. In The 33rd AAAI Conference on Artificial Intelligence. 5385--5392."},{"key":"e_1_3_2_1_27_1","first-page":"2315","article-title":"Does Tail Label Help for Large-Scale Multi-Label Learning","volume":"31","author":"Wei T.","year":"2020","unstructured":"T. Wei and Y.-F. Li . 2020 . Does Tail Label Help for Large-Scale Multi-Label Learning ? IEEE Trans. Neural Networks Learn. Syst. , Vol. 31 , 7 (2020), 2315 -- 2324 . T. Wei and Y.-F. Li. 2020. Does Tail Label Help for Large-Scale Multi-Label Learning? IEEE Trans. Neural Networks Learn. Syst., Vol. 31, 7 (2020), 2315--2324.","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/533"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 20th International Joint Conference on Artificial Intelligence","volume":"11","author":"Weston J.","unstructured":"J. Weston , S. Bengio , and N. Usunier . 2011. Wsabie: Scaling up to large vocabulary image annotation . In Proceedings of the 20th International Joint Conference on Artificial Intelligence , Vol. 11 . Barcelona, Spain, 2764--2770. J. Weston, S. Bengio, and N. Usunier. 2011. Wsabie: Scaling up to large vocabulary image annotation. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, Vol. 11. Barcelona, Spain, 2764--2770."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Xu C.","unstructured":"C. Xu , D.-C. Tao , and C. Xu . 2016. Robust extreme multi-label learning .. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . San Francisco, CA, 1275--1284. C. Xu, D.-C. Tao, and C. Xu. 2016. Robust extreme multi-label learning.. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, CA, 1275--1284."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10769"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Yen I. E.","unstructured":"I. E. Yen , X.-R. Huang , W. Dai , P. Ravikumar , I. Dhillon , and E. Xing . 2017. Ppdsparse: A parallel primal-dual sparse method for extreme classification . In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . Halifax, Canada, 545--553. I. E. Yen, X.-R. Huang, W. Dai, P. Ravikumar, I. Dhillon, and E. Xing. 2017. Ppdsparse: A parallel primal-dual sparse method for extreme classification. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax, Canada, 545--553."},{"key":"e_1_3_2_1_33_1","volume-title":"Attentionxml: Extreme multi-label text classification with multi-label attention based recurrent neural networks. Advances in Neural Information Processing Systems","author":"You R.","year":"2018","unstructured":"R. You , S. Dai , Z. Zhang , H. Mamitsuka , and S. Zhu . 2018 . Attentionxml: Extreme multi-label text classification with multi-label attention based recurrent neural networks. Advances in Neural Information Processing Systems (2018). R. You, S. Dai, Z. Zhang, H. Mamitsuka, and S. Zhu. 2018. Attentionxml: Extreme multi-label text classification with multi-label attention based recurrent neural networks. Advances in Neural Information Processing Systems (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 31st International Conference on Machine Learning","author":"Yu H.-F.","unstructured":"H.-F. Yu , P. Jain , P. Kar , and I. S. Dhillon . 2014. Large-scale multi-label learning with missing labels . In Proceedings of the 31st International Conference on Machine Learning . Beijing, China, 593--601. H.-F. Yu, P. Jain, P. Kar, and I. S. Dhillon. 2014. Large-scale multi-label learning with missing labels. In Proceedings of the 31st International Conference on Machine Learning. Beijing, China, 593--601."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.019"}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event Singapore","acronym":"KDD '21","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467223","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3467223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:28Z","timestamp":1750191508000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":35,"alternative-id":["10.1145\/3447548.3467223","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3467223","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}