{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:42:31Z","timestamp":1774456951977,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["347709, 348215"],"award-info":[{"award-number":["347709, 348215"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591699","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"760-769","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6847-5836","authenticated-orcid":false,"given":"Siddhant","family":"Kharbanda","sequence":"first","affiliation":[{"name":"Aalto University & Microsoft Corporation, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7949-8062","authenticated-orcid":false,"given":"Atmadeep","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3007-0109","authenticated-orcid":false,"given":"Devaansh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Aalto University & BITS Pilani, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-8104","authenticated-orcid":false,"given":"Akash","family":"Palrecha","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3787-8971","authenticated-orcid":false,"given":"Rohit","family":"Babbar","sequence":"additional","affiliation":[{"name":"Aalto University & University of Bath, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_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.","DOI":"10.1145\/2488388.2488391"},{"key":"e_1_3_2_1_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.","DOI":"10.1145\/3018661.3018741"},{"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 K. Dahiya H. Jain P. Kar A. Mittal Y. Prabhu and M. Varma. 2016. The extreme classification repository: Multi-label datasets and code."},{"key":"e_1_3_2_1_5_1","unstructured":"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_1_6_1","doi-asserted-by":"crossref","unstructured":"Ilias Chalkidis Manos Fergadiotis Prodromos Malakasiotis and Ion Androut- sopoulos. 2019. Large-scale multi-label text classification on eu legislation. arXiv preprint arXiv:1906.02192.","DOI":"10.18653\/v1\/P19-1636"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"W-C. Chang H.-F. Yu K. Zhong Y. Yang and I. Dhillon. 2020. Taming Pretrained Transformers for Extreme Multi-label Text Classification. In KDD.","DOI":"10.1145\/3394486.3403368"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Wei-Cheng Chang Daniel Jiang Hsiang-Fu Yu Choon-Hui Teo Jiong Zhang Kai Zhong Kedarnath Kolluri Qie Hu Nikhil Shandilya Vyacheslav Ievgrafov et al. 2021. Extreme multi-label learning for semantic matching in product search. arXiv preprint arXiv:2106.12657.","DOI":"10.1145\/3447548.3467092"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Dahiya K.","unstructured":"K. Dahiya, A. Agarwal, D. Saini, K. Gururaj, J. Jiao, A. Singh, S. Agarwal, P. Kar, and M. Varma. 2021. Siamesexml: Siamese networks meet extreme classifiers with 100m labels. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_1_10_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. 2021. 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_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159659"},{"key":"e_1_3_2_1_12_1","volume-title":"Liblinear: A library for large linear classification. the Journal of machine Learning research, 9:1871--1874.","author":"Fan Rong-En","year":"2008","unstructured":"Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. Liblinear: A library for large linear classification. the Journal of machine Learning research, 9:1871--1874."},{"key":"e_1_3_2_1_13_1","first-page":"3929","volume-title":"International conference on machine learning","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning, pages 3929--3938. PMLR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"e_1_3_2_1_15_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.","DOI":"10.1145\/2939672.2939756"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16974"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Armand Joulin Edouard Grave Piotr Bojanowski and Tomas Mikolov. 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759.","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Vladimir Karpukhin Barlas O?uz Sewon Min Patrick Lewis Ledell Wu Sergey Edunov Danqi Chen and Wen-tau Yih. 2020. Dense passage retrieval for open- domain question answering. arXiv preprint arXiv:2004.04906.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05888-2"},{"key":"e_1_3_2_1_21_1","unstructured":"Siddhant Kharbanda Atmadeep Banerjee Erik Schultheis and Rohit Babbar. 2022. CascadeXML: Rethinking transformers for end-to-end multi-resolution training in extreme multi-label classification. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Y. Kim. 2014. Convolutional Neural Networks for Sentence Classification. In EMNLP.","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"J. Liu W. Chang Y. Wu and Y. Yang. 2017. Deep Learning for Extreme Multi-label Text Classification. In SIGIR.","DOI":"10.1145\/3077136.3080834"},{"key":"e_1_3_2_1_25_1","volume-title":"Hao Tian, Hua Wu, Shuaiqiang Wang, Dawei Yin, et al.","author":"Lu Yuxiang","year":"2022","unstructured":"Yuxiang Lu, Yiding Liu, Jiaxiang Liu, Yunsheng Shi, Zhengjie Huang, Shikun Feng Yu Sun, Hao Tian, Hua Wu, Shuaiqiang Wang, Dawei Yin, et al. 2022. Ernie-search: Bridging cross-encoder with dual-encoder via self on-the-fly distillation for dense passage retrieval. arXiv preprint arXiv:2205.09153."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_27_1","unstructured":"T. Mikolov I. Sutskever K. Chen G. Corrado and J. Dean. 2013. Distributed Representations of Words and Phrases and Their Compositionality. In NIPS."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the ACM International Conference on Web Search and Data Mining.","author":"Mittal A.","unstructured":"A. Mittal, K. Dahiya, S. Agrawal, D. Saini, S. Agarwal, P. Kar, and M. Varma. 2021. Decaf: Deep extreme classification with label features. In Proceedings of the ACM International Conference on Web Search and Data Mining."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of The ACM International World Wide Web Conference.","author":"Mittal A.","unstructured":"A. Mittal, N. Sachdeva, S. Agrawal, S. Agarwal, P. Kar, and M. Varma. 2021. Eclare: Extreme classification with label graph correlations. In Proceedings of The ACM International World Wide Web Conference."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"J. Pennington R. Socher and C. D. Manning. 2014. GloVe: Global Vectors for Word Representation. In EMNLP.","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_31_1","volume-title":"Manning","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington, R. Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In EMNLP."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185998"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450139"},{"key":"e_1_3_2_1_34_1","volume-title":"Daxiang Dong, Hua Wu, and Haifeng Wang.","author":"Qu Yingqi","year":"2020","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2020. Rocketqa: An optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191."},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Reif Emily","year":"2019","unstructured":"Emily Reif, Ann Yuan, Martin Wattenberg, Fernanda B Viegas, Andy Coenen, Adam Pearce, and Been Kim. 2019. Visualizing and measuring the geometry of bert. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of The ACM International World Wide Web Conference.","author":"Saini D.","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 Proceedings of The ACM International World Wide Web Conference."},{"key":"e_1_3_2_1_37_1","first-page":"1","volume-title":"Machine Learning","author":"Schultheis Erik","year":"2022","unstructured":"Erik Schultheis and Rohit Babbar. 2022. Speeding-up one-versus-all training for extreme classification via mean-separating initialization. Machine Learning, pages 1--24."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539466"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783307"},{"key":"e_1_3_2_1_41_1","first-page":"236","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics: Industry Track","author":"Tayal Kshitij","year":"2020","unstructured":"Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian, and Vipin Kumar. 2020. Regularized graph convolutional networks for short text classification. In Proceedings of the 28th International Conference on Computational Linguistics: Industry Track, pages 236--242."},{"key":"e_1_3_2_1_42_1","unstructured":"Iulia Turc Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. Well-read students learn better: On the importance of pre-training compact models. arXiv preprint arXiv:1908.08962v2."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1216"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Jin Wang Zhongyuan Wang Dawei Zhang and Jun Yan. 2017. Combining knowledge with deep convolutional neural networks for short text classification. In IJCAI.","DOI":"10.24963\/ijcai.2017\/406"},{"key":"e_1_3_2_1_45_1","unstructured":"Zhongyuan Wang and Haixun Wang. 2016. Understanding short texts. In the Association for Computational Linguistics (ACL) (Tutorial)."},{"key":"e_1_3_2_1_46_1","volume-title":"Ju- naid Ahmed, and Arnold Overwijk","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Ju- naid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808."},{"key":"e_1_3_2_1_47_1","unstructured":"H. Ye Z. Chen D.-H. Wang and Davison B. D. 2020. Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification. In ICML."},{"key":"e_1_3_2_1_48_1","volume-title":"Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. In Neurips.","author":"You R.","year":"2019","unstructured":"R. You, Z. Zhang, Z. Wang, S. Dai, H. Mamitsuka, and S. Zhu. 2019. Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. In Neurips."},{"key":"e_1_3_2_1_49_1","volume-title":"Pecos: Prediction for enormous and correlated output spaces. arXiv preprint arXiv:2010.05878.","author":"Yu Hsiang-Fu","year":"2020","unstructured":"Hsiang-Fu Yu, Kai Zhong, and Inderjit S Dhillon. 2020. Pecos: Prediction for enormous and correlated output spaces. arXiv preprint arXiv:2010.05878."},{"key":"e_1_3_2_1_50_1","unstructured":"Hang Zhang Yeyun Gong Yelong Shen Jiancheng Lv Nan Duan and Weizhu Chen. 2021. Adversarial retriever-ranker for dense text retrieval. arXiv preprint arXiv:2110.03611."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591699","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:00Z","timestamp":1750178820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":50,"alternative-id":["10.1145\/3539618.3591699","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591699","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}