{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:00:47Z","timestamp":1772906447857,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":61,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599301","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"358-367","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep Encoders with Auxiliary Parameters for Extreme Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1500-0295","authenticated-orcid":false,"given":"Kunal","family":"Dahiya","sequence":"first","affiliation":[{"name":"IIT Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0048-1118","authenticated-orcid":false,"given":"Sachin","family":"Yadav","sequence":"additional","affiliation":[{"name":"Microsoft Research, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8146-2854","authenticated-orcid":false,"given":"Sushant","family":"Sondhi","sequence":"additional","affiliation":[{"name":"IIT Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6057-4351","authenticated-orcid":false,"given":"Deepak","family":"Saini","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1654-3766","authenticated-orcid":false,"given":"Sonu","family":"Mehta","sequence":"additional","affiliation":[{"name":"Microsoft Research & IIT Delhi, Bangalore & New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4779-9588","authenticated-orcid":false,"given":"Jian","family":"Jiao","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5714-3921","authenticated-orcid":false,"given":"Sumeet","family":"Agarwal","sequence":"additional","affiliation":[{"name":"IIT Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2096-5267","authenticated-orcid":false,"given":"Purushottam","family":"Kar","sequence":"additional","affiliation":[{"name":"IIT Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-6613","authenticated-orcid":false,"given":"Manik","family":"Varma","sequence":"additional","affiliation":[{"name":"Microsoft Research, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","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 WWW.  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 WWW.","DOI":"10.1145\/2488388.2488391"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"R. Babbar and B. Sch\u00f6lkopf. 2017. DiSMEC: Distributed Sparse Machines for Extreme Multi-label Classification. In WSDM.  R. Babbar and B. Sch\u00f6lkopf. 2017. DiSMEC: Distributed Sparse Machines for Extreme Multi-label Classification. In WSDM.","DOI":"10.1145\/3018661.3018741"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"R. Babbar and B. Sch\u00f6lkopf. 2019. Data scarcity robustness and extreme multi-label classification. ML (2019).  R. Babbar and B. Sch\u00f6lkopf. 2019. Data scarcity robustness and extreme multi-label classification. ML (2019).","DOI":"10.1007\/s10994-019-05791-5"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"E. J. Barezi I. D. W. P. Fung and H. R. Rabiee. 2019. A Submodular Feature-Aware Framework for Label Subset Selection in Extreme Classification Problems. In NAACL.  E. J. Barezi I. D. W. P. Fung and H. R. Rabiee. 2019. A Submodular Feature-Aware Framework for Label Subset Selection in Extreme Classification Problems. In NAACL.","DOI":"10.18653\/v1\/N19-1106"},{"key":"e_1_3_2_2_5_1","unstructured":"K. Bhatia K. Dahiya H. Jain P. Kar A. Mittal Y. Prabhu and M. Varma. 2016. The Extreme Classification Repository: Multi-label Datasets & Code. http:\/\/manikvarma.org\/downloads\/XC\/XMLRepository.html  K. Bhatia K. Dahiya H. Jain P. Kar A. Mittal Y. Prabhu and M. Varma. 2016. The Extreme Classification Repository: Multi-label Datasets & Code. http:\/\/manikvarma.org\/downloads\/XC\/XMLRepository.html"},{"key":"e_1_3_2_2_6_1","unstructured":"K. Bhatia H. Jain P. Kar M. Varma and P. Jain. 2015. Sparse Local Embeddings for Extreme Multi-label Classification. In NIPS.  K. Bhatia H. Jain P. Kar M. Varma and P. Jain. 2015. Sparse Local Embeddings for Extreme Multi-label Classification. In NIPS."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"I. Chalkidis M. Fergadiotis P. Malakasiotis N. Aletras and I. Androutsopoulos. 2019. Extreme Multi-Label Legal Text Classification: A case study in EU Legislation. In ACL.  I. Chalkidis M. Fergadiotis P. Malakasiotis N. Aletras and I. Androutsopoulos. 2019. Extreme Multi-Label Legal Text Classification: A case study in EU Legislation. In ACL.","DOI":"10.18653\/v1\/W19-2209"},{"key":"e_1_3_2_2_8_1","unstructured":"W-C. Chang F.-X. Yu Y.-W. Chang Y. Yang and S. Kumar. 2020a. Pre-training Tasks for Embedding-based Large-scale Retrieval. In ICLR.  W-C. Chang F.-X. Yu Y.-W. Chang Y. Yang and S. Kumar. 2020a. Pre-training Tasks for Embedding-based Large-scale Retrieval. In ICLR."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"W.-C. Chang H.-F. Yu K. Zhong Y. Yang and I. S. Dhillon. 2020b. Taming Pretrained Transformers for Extreme Multi-label Text Classification. In KDD.  W.-C. Chang H.-F. Yu K. Zhong Y. Yang and I. S. Dhillon. 2020b. Taming Pretrained Transformers for Extreme Multi-label Text Classification. In KDD.","DOI":"10.1145\/3394486.3403368"},{"key":"e_1_3_2_2_10_1","unstructured":"T. Chen S. Kornblith M. Norouzi and G. Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML.  T. Chen S. Kornblith M. Norouzi and G. Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"N. Craswell D. Campos B. Mitra E. Yilmaz and B. Billerbeck. 2020a. ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Search. arxiv: 2006.05324 [cs.IR]  N. Craswell D. Campos B. Mitra E. Yilmaz and B. Billerbeck. 2020a. ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Search. arxiv: 2006.05324 [cs.IR]","DOI":"10.1145\/3340531.3412779"},{"key":"e_1_3_2_2_12_1","volume-title":"Overview of the TREC 2019 deep learning track. arxiv","author":"Craswell N.","year":"2003","unstructured":"N. Craswell , B. Mitra , E. Yilmaz , D. Campos , and E. M. Voorhees . 2020b . Overview of the TREC 2019 deep learning track. arxiv : 2003 .07820 N. Craswell, B. Mitra, E. Yilmaz, D. Campos, and E. M. Voorhees. 2020b. Overview of the TREC 2019 deep learning track. arxiv: 2003.07820"},{"key":"e_1_3_2_2_13_1","volume-title":"SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels. In ICML.","author":"Dahiya K.","unstructured":"K. Dahiya , A. Agarwal , D. Saini , K. Gururaj , J. Jiao , A. Singh , S. Agarwal , P. Kar , and M. Varma . 2021a . SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels. In ICML. K. Dahiya, A. Agarwal, D. Saini, K. Gururaj, J. Jiao, A. Singh, S. Agarwal, P. Kar, and M. Varma. 2021a. SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels. In ICML."},{"key":"e_1_3_2_2_14_1","volume-title":"NGAME: Negative mining-aware mini-batching for extreme classification. In WSDM.","author":"Dahiya K.","year":"2023","unstructured":"K. Dahiya , N. Gupta , D. Saini , A. Soni , Y. Wang , K. Dave , J. Jiao , K. Gururaj , P. Dey , A. Singh , D. Hada , V. Jain , B. Paliwal , A. Mittal , S. Mehta , R. Ramjee , S. Agarwal , P. Kar , and M. Varma . 2023 . NGAME: Negative mining-aware mini-batching for extreme classification. In WSDM. K. Dahiya, N. Gupta, D. Saini, A. Soni, Y. Wang, K. Dave, J. Jiao, K. Gururaj, P. Dey, A. Singh, D. Hada, V. Jain, B. Paliwal, A. Mittal, S. Mehta, R. Ramjee, S. Agarwal, P. Kar, and M. Varma. 2023. NGAME: Negative mining-aware mini-batching for extreme classification. In WSDM."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"K. Dahiya D. Saini A. Mittal A. Shaw K. Dave A. Soni H. Jain S. Agarwal and M. Varma. 2021b. DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents. In WSDM.  K. Dahiya D. Saini A. Mittal A. Shaw K. Dave A. Soni H. Jain S. Agarwal and M. Varma. 2021b. DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents. In WSDM.","DOI":"10.1145\/3437963.3441810"},{"key":"e_1_3_2_2_16_1","volume-title":"BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL","author":"Devlin J.","year":"2019","unstructured":"J. Devlin , M. W. Chang , K. Lee , and K. Toutanova . 2019 . BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL (2019). J. Devlin, M. W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL (2019)."},{"key":"e_1_3_2_2_17_1","volume-title":"VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In BMVC.","author":"Faghri F.","year":"2018","unstructured":"F. Faghri , D.-J. Fleet , J.-R. Kiros , and S. Fidler . 2018 . VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In BMVC. F. Faghri, D.-J. Fleet, J.-R. Kiros, and S. Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In BMVC."},{"key":"e_1_3_2_2_18_1","unstructured":"C. Guo A. Mousavi X. Wu D.-N. Holtmann-Rice S. Kale S. Reddi and S. Kumar. 2019. Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces. In NeurIPS.  C. Guo A. Mousavi X. Wu D.-N. Holtmann-Rice S. Kale S. Reddi and S. Kumar. 2019. Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces. In NeurIPS."},{"key":"e_1_3_2_2_19_1","volume-title":"ELIAS: End-to-End Learning to Index and Search in Large Output Spaces. In NeurIPS.","author":"Gupta N.","year":"2022","unstructured":"N. Gupta , P. H. Chen , H.-F. Yu , Cho- J. Hsieh , and I. S. Dhillon . 2022 . ELIAS: End-to-End Learning to Index and Search in Large Output Spaces. In NeurIPS. N. Gupta, P. H. Chen, H.-F. Yu, Cho-J. Hsieh, and I. S. Dhillon. 2022. ELIAS: End-to-End Learning to Index and Search in Large Output Spaces. In NeurIPS."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"K. He Haoqi Fan Yuxin W. S. Xie and R. Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In CVPR.  K. He Haoqi Fan Yuxin W. S. Xie and R. Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"H. Jain Y. Prabhu and M. Varma. 2016. Extreme Multi-label Loss Functions for Recommendation Tagging Ranking and Other Missing Label Applications. In KDD.  H. Jain Y. Prabhu and M. Varma. 2016. Extreme Multi-label Loss Functions for Recommendation Tagging Ranking and Other Missing Label Applications. In KDD.","DOI":"10.1145\/2939672.2939756"},{"key":"e_1_3_2_2_23_1","unstructured":"K. Jasinska K. Dembczynski R. Busa-Fekete K. Pfannschmidt T. Klerx and E. Hullermeier. 2016. Extreme F-measure Maximization using Sparse Probability Estimates. In ICML.  K. Jasinska K. Dembczynski R. Busa-Fekete K. Pfannschmidt T. Klerx and E. Hullermeier. 2016. Extreme F-measure Maximization using Sparse Probability Estimates. In ICML."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"T. Jiang D. Wang L. Sun H. Yang Z. Zhao and F. Zhuang. 2021. LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification. In AAAI.  T. Jiang D. Wang L. Sun H. Yang Z. Zhao and F. Zhuang. 2021. LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification. In AAAI.","DOI":"10.1609\/aaai.v35i9.16974"},{"key":"e_1_3_2_2_25_1","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. In ICLR.  B. Kang S. Xie M. Rohrbach Z. Yan A. Gordo J. Feng and Y. Kalantidis. 2020. Decoupling representation and classifier for long-tailed recognition. In ICLR."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"V. Karpukhin B. Oguz S. Min P. Lewis L. Wu S. Edunov D. Chen and W.-T. Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP.  V. Karpukhin B. Oguz S. Min P. Lewis L. Wu S. Edunov D. Chen and W.-T. Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"S. Khandagale H. Xiao and R. Babbar. 2020. Bonsai: diverse and shallow trees for extreme multi-label classification. ML (2020).  S. Khandagale H. Xiao and R. Babbar. 2020. Bonsai: diverse and shallow trees for extreme multi-label classification. ML (2020).","DOI":"10.1007\/s10994-020-05888-2"},{"key":"e_1_3_2_2_28_1","unstructured":"S. Kharbanda A. Banerjee E. Schultheis and R. Babbar. 2022. CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification. In NeurIPS.  S. Kharbanda A. Banerjee E. Schultheis and R. Babbar. 2022. CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification. In NeurIPS."},{"key":"e_1_3_2_2_29_1","volume-title":"Colbert: Efficient and effective passage search via contextualized late interaction over bert. In SIGIR.","author":"Khattab O.","year":"2020","unstructured":"O. Khattab and M. Zaharia . 2020 . Colbert: Efficient and effective passage search via contextualized late interaction over bert. In SIGIR. O. Khattab and M. Zaharia. 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In SIGIR."},{"key":"e_1_3_2_2_30_1","unstructured":"Shuqi Lu Di He Chenyan Xiong Guolin Ke Waleed Malik Zhicheng Dou Paul Bennett Tieyan Liu and Arnold Overwijk. 2021. Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder. arXiv:2102.09206 [cs.LG].  Shuqi Lu Di He Chenyan Xiong Guolin Ke Waleed Malik Zhicheng Dou Paul Bennett Tieyan Liu and Arnold Overwijk. 2021. Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder. arXiv:2102.09206 [cs.LG]."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"W. Lu J. Jiao and R. Zhang. 2020. TwinBERT: Distilling Knowledge to Twin-Structured Compressed BERT Models for Large-Scale Retrieval. In CIKM.  W. Lu J. Jiao and R. Zhang. 2020. TwinBERT: Distilling Knowledge to Twin-Structured Compressed BERT Models for Large-Scale Retrieval. In CIKM.","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"A. Y. Malkov and D. A. Yashunin. 2020. Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs. TPAMI (2020).  A. Y. Malkov and D. A. Yashunin. 2020. Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs. TPAMI (2020).","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_2_33_1","unstructured":"T. K. R. Medini Q. Huang Y. Wang V. Mohan and A. Shrivastava. 2019. Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products. In NeurIPS.  T. K. R. Medini Q. Huang Y. Wang V. Mohan and A. Shrivastava. 2019. Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products. In NeurIPS."},{"key":"e_1_3_2_2_34_1","volume":"201","author":"Mikolov T.","unstructured":"T. Mikolov , I. Sutskever , K. Chen , G. Corrado , and J. Dean. 201 3. Distributed Representations of Words and Phrases and Their Compositionality. In NIPS. T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean. 2013. Distributed Representations of Words and Phrases and Their Compositionality. In NIPS.","journal-title":"J. Dean."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"P. Mineiro and N. Karampatziakis. 2015. Fast Label Embeddings via Randomized Linear Algebra. In ECML\/PKDD.  P. Mineiro and N. Karampatziakis. 2015. Fast Label Embeddings via Randomized Linear Algebra. In ECML\/PKDD.","DOI":"10.1007\/978-3-319-23528-8_3"},{"key":"e_1_3_2_2_36_1","volume-title":"DECAF: Deep Extreme Classification with Label Features. In WSDM.","author":"Mittal A.","year":"2021","unstructured":"A. Mittal , K. Dahiya , S. Agrawal , D. Saini , S. Agarwal , P. Kar , and M. Varma . 2021 a. DECAF: Deep Extreme Classification with Label Features. In WSDM. A. Mittal, K. Dahiya, S. Agrawal, D. Saini, S. Agarwal, P. Kar, and M. Varma. 2021a. DECAF: Deep Extreme Classification with Label Features. In WSDM."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"A. Mittal K. Dahiya S. Malani J. Ramaswamy S. Kuruvilla J. Ajmera K. Chang S. Agrawal P. Kar and M. Varma. 2022. Multimodal Extreme Classification. In CVPR.  A. Mittal K. Dahiya S. Malani J. Ramaswamy S. Kuruvilla J. Ajmera K. Chang S. Agrawal P. Kar and M. Varma. 2022. Multimodal Extreme Classification. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01207"},{"key":"e_1_3_2_2_38_1","volume-title":"ECLARE: Extreme Classification with Label Graph Correlations. In WWW.","author":"Mittal A.","year":"2021","unstructured":"A. Mittal , N. Sachdeva , S. Agrawal , S. Agarwal , P. Kar , and M. Varma . 2021 b. ECLARE: Extreme Classification with Label Graph Correlations. In WWW. A. Mittal, N. Sachdeva, S. Agrawal, S. Agarwal, P. Kar, and M. Varma. 2021b. ECLARE: Extreme Classification with Label Graph Correlations. In WWW."},{"key":"e_1_3_2_2_39_1","unstructured":"A. Niculescu-Mizil and E. Abbasnejad. 2017. Label Filters for Large Scale Multilabel Classification. In AISTATS.  A. Niculescu-Mizil and E. Abbasnejad. 2017. Label Filters for Large Scale Multilabel Classification. In AISTATS."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Y. Prabhu A. Kag S. Gopinath K. Dahiya S. Harsola R. Agrawal and M. Varma. 2018a. Extreme multi-label learning with label features for warm-start tagging ranking and recommendation. In WSDM.  Y. Prabhu A. Kag S. Gopinath K. Dahiya S. Harsola R. Agrawal and M. Varma. 2018a. Extreme multi-label learning with label features for warm-start tagging ranking and recommendation. In WSDM.","DOI":"10.1145\/3159652.3159660"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185998"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Y. Prabhu A. Kusupati N. Gupta and M. Varma. 2020. Extreme Regression for Dynamic Search Advertising. In WSDM.  Y. Prabhu A. Kusupati N. Gupta and M. Varma. 2020. Extreme Regression for Dynamic Search Advertising. In WSDM.","DOI":"10.1145\/3336191.3371768"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Y. Prabhu and M. Varma. 2014. FastXML: A Fast Accurate and Stable Tree-classifier for eXtreme Multi-label Learning. In KDD.  Y. Prabhu and M. Varma. 2014. FastXML: A Fast Accurate and Stable Tree-classifier for eXtreme Multi-label Learning. In KDD.","DOI":"10.1145\/2623330.2623651"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"M. Qaraei E. Schultheis P. Gupta and R. Babbar. 2021. Convex Surrogates for Unbiased Loss Functions in Extreme Classification With Missing Labels. In The WebConf.  M. Qaraei E. Schultheis P. Gupta and R. Babbar. 2021. Convex Surrogates for Unbiased Loss Functions in Extreme Classification With Missing Labels. In The WebConf.","DOI":"10.1145\/3442381.3450139"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Y. Qu Y. Ding J. Liu K. Liu R. Ren W. X. Zhao D. Dong H. Wu and H. Wang. 2021. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering.  Y. Qu Y. Ding J. Liu K. Liu R. Ren W. X. Zhao D. Dong H. Wu and H. Wang. 2021. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering.","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_2_46_1","unstructured":"A. S. Rawat A. K. Menon W. Jitkrittum S. Jayasumana F. X. Yu S. Reddi and S. Kumar. 2021. Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces. In ICML.  A. S. Rawat A. K. Menon W. Jitkrittum S. Jayasumana F. X. Yu S. Reddi and S. Kumar. 2021. Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces. In ICML."},{"key":"e_1_3_2_2_47_1","unstructured":"S. J. Reddi S. Kale F.X. Yu D. N. H. Rice J. Chen and S. Kumar. 2019. Stochastic Negative Mining for Learning with Large Output Spaces. In AISTATS.  S. J. Reddi S. Kale F.X. Yu D. N. H. Rice J. Chen and S. Kumar. 2019. Stochastic Negative Mining for Learning with Large Output Spaces. In AISTATS."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"T. Renter A. Borisov and M. De Rijke. 2016. Siamese CBOW: Optimizing word embeddings for sentence representations. In ACL.  T. Renter A. Borisov and M. De Rijke. 2016. Siamese CBOW: Optimizing word embeddings for sentence representations. In ACL.","DOI":"10.18653\/v1\/P16-1089"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"D. Saini A.K. Jain K. Dave J. Jiao A. Singh R. Zhang and M. Varma. 2021. GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification. In WWW.  D. Saini A.K. Jain K. Dave J. Jiao A. Singh R. Zhang and M. Varma. 2021. GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification. In WWW.","DOI":"10.1145\/3442381.3449937"},{"key":"e_1_3_2_2_50_1","unstructured":"V. Sanh L. Debut J. Chaumond and T. Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. ArXiv (2019).  V. Sanh L. Debut J. Chaumond and T. Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. ArXiv (2019)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"E. Schultheis M. Wydmuch R. Babbar and K. Dembczynski. 2022. On Missing Labels Long-Tails and Propensities in Extreme Multi-Label Classification. In KDD.  E. Schultheis M. Wydmuch R. Babbar and K. Dembczynski. 2022. On Missing Labels Long-Tails and Propensities in Extreme Multi-Label Classification. In KDD.","DOI":"10.1145\/3534678.3539466"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Y. Tagami. 2017. AnnexML: Approximate Nearest Neighbor Search for Extreme Multi-label Classification. In KDD.  Y. Tagami. 2017. AnnexML: Approximate Nearest Neighbor Search for Extreme Multi-label Classification. In KDD.","DOI":"10.1145\/3097983.3097987"},{"key":"e_1_3_2_2_53_1","unstructured":"W. Wang F. Wei L. Dong H. Bao N. Yang and M. Zhou. 2020. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. arxiv: 2002.10957 [cs.CL]  W. Wang F. Wei L. Dong H. Bao N. Yang and M. Zhou. 2020. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. arxiv: 2002.10957 [cs.CL]"},{"key":"e_1_3_2_2_54_1","volume-title":"A Survey on Extreme Multi-label Learning. arXiv preprint arXiv:2210.03968","author":"Wei T.","year":"2022","unstructured":"T. Wei , Z. Mao , J.-X. Shi , Y.-F. Li , and M.-L. Zhang . 2022. A Survey on Extreme Multi-label Learning. arXiv preprint arXiv:2210.03968 ( 2022 ). T. Wei, Z. Mao, J.-X. Shi, Y.-F. Li, and M.-L. Zhang. 2022. A Survey on Extreme Multi-label Learning. arXiv preprint arXiv:2210.03968 (2022)."},{"key":"e_1_3_2_2_55_1","unstructured":"M. Wydmuch K. Jasinska M. Kuznetsov R. Busa-Fekete and K. Dembczynski. 2018. A no-regret generalization of hierarchical softmax to extreme multi-label classification. In NIPS.  M. Wydmuch K. Jasinska M. Kuznetsov R. Busa-Fekete and K. Dembczynski. 2018. A no-regret generalization of hierarchical softmax to extreme multi-label classification. In NIPS."},{"key":"e_1_3_2_2_56_1","unstructured":"L. Xiong C. Xiong Y. Li K.-F. Tang J. Liu P. Bennett J. Ahmed and A. Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In ICLR.  L. Xiong C. Xiong Y. Li K.-F. Tang J. Liu P. Bennett J. Ahmed and A. Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In ICLR."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"C. Xu D. Tao and C. Xu. 2016. Robust Extreme Multi-label Learning. In KDD.  C. Xu D. Tao and C. Xu. 2016. Robust Extreme Multi-label Learning. In KDD.","DOI":"10.1145\/2939672.2939798"},{"key":"e_1_3_2_2_58_1","unstructured":"J. Yang Z. Liu S. Xiao C. Li D. Lian S. Agrawal A. Singh G. Sun and X. Xie. 2021. GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph. In NeurIPS.  J. Yang Z. Liu S. Xiao C. Li D. Lian S. Agrawal A. Singh G. Sun and X. Xie. 2021. GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph. In NeurIPS."},{"key":"e_1_3_2_2_59_1","unstructured":"H. Ye Z. Chen D.-H. Wang and B. D. Davison. 2020. Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification. In ICML.  H. Ye Z. Chen D.-H. Wang and B. D. Davison. 2020. Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification. In ICML."},{"key":"e_1_3_2_2_60_1","unstructured":"R. You S. Dai Z. Zhang H. Mamitsuka and S. Zhu. 2019. AttentionXML: Extreme Multi-Label Text Classification with Multi-Label Attention Based Recurrent Neural Networks. In NeurIPS.  R. You S. Dai Z. Zhang H. Mamitsuka and S. Zhu. 2019. AttentionXML: Extreme Multi-Label Text Classification with Multi-Label Attention Based Recurrent Neural Networks. In NeurIPS."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"J. Zhang W. C. Chang H. F. Yu and I. Dhillon. 2021. Fast multi-resolution transformer fine-tuning for extreme multi-label text classification. In NeurIPS. io  J. Zhang W. C. Chang H. F. Yu and I. Dhillon. 2021. Fast multi-resolution transformer fine-tuning for extreme multi-label text classification. In NeurIPS. io","DOI":"10.1145\/3394486.3403368"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599301","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:47Z","timestamp":1750178267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":61,"alternative-id":["10.1145\/3580305.3599301","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599301","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"}}]}}