{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:20:03Z","timestamp":1759969203552,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3715230","type":"proceedings-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:20:01Z","timestamp":1748017201000},"page":"394-402","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Graph Regularized Encoder Training for Extreme Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4137-0126","authenticated-orcid":false,"given":"Anshul","family":"Mittal","sequence":"first","affiliation":[{"name":"Microsoft, Noida, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1689-0457","authenticated-orcid":false,"given":"Shikhar","family":"Mohan","sequence":"additional","affiliation":[{"name":"Microsoft, Bengaluru, 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, Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3058-2852","authenticated-orcid":false,"given":"Siddarth","family":"Asokan","sequence":"additional","affiliation":[{"name":"Microsoft Research, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4647-3304","authenticated-orcid":false,"given":"Suchith Chidananda","family":"Prabhu","sequence":"additional","affiliation":[{"name":"IIT Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6134-471X","authenticated-orcid":false,"given":"Lakshya","family":"Kumar","sequence":"additional","affiliation":[{"name":"Microsoft, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4486-2879","authenticated-orcid":false,"given":"Pankaj","family":"Malhotra","sequence":"additional","affiliation":[{"name":"Microsoft, Noida, 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, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0669-5283","authenticated-orcid":false,"given":"Amit","family":"Singh","sequence":"additional","affiliation":[{"name":"Microsoft, Bengaluru, India"}],"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, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9419-7486","authenticated-orcid":false,"given":"Soumen","family":"Chakrabarti","sequence":"additional","affiliation":[{"name":"IIT Bombay, Mumbai, 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, Bengaluru, India and IIT Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Efficient large scale language modeling with mixtures of experts. arXiv preprint arXiv:2112.10684","author":"Artetxe M.","year":"2021","unstructured":"M. Artetxe, S. Bhosale, N. Goyal, T. Mihaylov, M. Ott, S. Shleifer, X.-V. Lin, J. Du, S. Iyer, R. Pasunuru, et al. Efficient large scale language modeling with mixtures of experts. arXiv preprint arXiv:2112.10684, 2021."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018741"},{"key":"e_1_3_2_2_3_1","volume-title":"The Extreme Classification Repository: Multi-label Datasets & Code","author":"Bhatia K.","year":"2016","unstructured":"K. Bhatia, K. Dahiya, H. Jain, A. Mittal, Y. Prabhu, and M. Varma. The Extreme Classification Repository: Multi-label Datasets & Code, 2016. URL http:\/\/manikvarma.org\/downloads\/XC\/XMLRepository.html."},{"key":"e_1_3_2_2_4_1","volume-title":"ACL","author":"Chalkidis I.","year":"2019","unstructured":"I. Chalkidis, M. Fergadiotis, P. Malakasiotis, N. Aletras, and I. Androutsopoulos. Extreme Multi-Label Legal Text Classification: A case study in EU Legislation. In ACL, 2019."},{"key":"e_1_3_2_2_5_1","volume-title":"CoRR","author":"Chang C.","year":"2019","unstructured":"C. .W. Chang, H. F. Yu, K. Zhong, Y. Yang, and I. S. Dhillon. A Modular Deep Learning Approach for Extreme Multi-label Text Classification. CoRR, 2019."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403368"},{"key":"e_1_3_2_2_7_1","volume-title":"ICLR","author":"Chen J.","year":"2018","unstructured":"J. Chen, T. Ma, and C. Xiao. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. In ICLR, 2018."},{"key":"e_1_3_2_2_8_1","volume-title":"ICML","author":"Chen T.","year":"2020","unstructured":"T. Chen, S. Kornblith, M. Norouzi, and G. Hinton. A simple framework for contrastive learning of visual representations. In ICML, 2020."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_3_2_2_10_1","volume-title":"ICML","author":"Chien E.","year":"2023","unstructured":"E. Chien, J. Zhang, C. Hsieh, J. Jiang, W. Chang, O. Milenkovic, and H. Yu. PINA: Leveraging side information in eXtreme multi-label classification via predicted instance neighborhood aggregation. In ICML, 2023."},{"key":"e_1_3_2_2_11_1","volume-title":"SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels. In ICML","author":"Dahiya K.","year":"2021","unstructured":"K. Dahiya, A. Agarwal, D. Saini, K. Gururaj, J. Jiao, A. Singh, S. Agarwal, P. Kar, and M. Varma. SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels. In ICML, 2021."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441810"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570392"},{"key":"e_1_3_2_2_14_1","volume-title":"BMVC","author":"Faghri F.","year":"2018","unstructured":"F. Faghri, D.-J. Fleet, J.-R. Kiros, and S. Fidler. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In BMVC, 2018."},{"key":"e_1_3_2_2_15_1","volume-title":"NeurIPS","author":"Guo C.","year":"2019","unstructured":"C. Guo, A. Mousavi, X. Wu, D.-N. Holtmann-Rice, S. Kale, S. Reddi, and S. Kumar. Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces. In NeurIPS, 2019."},{"key":"e_1_3_2_2_16_1","volume-title":"ICLR","author":"Gupta N.","year":"2023","unstructured":"N. Gupta, D. Khatri, A. S Rawat, S. Bhojanapalli, P. Jain, and I. S Dhillon. Efficacy of dual-encoders for extreme multi-label classification. In ICLR, 2023."},{"key":"e_1_3_2_2_17_1","volume-title":"ICLR","author":"Gupta N.","year":"2024","unstructured":"N. Gupta, F. Devvrit, A. S. Rawat, S. Bhojanapalli, P. Jain, and I. S. Dhillon. Dualencoders for extreme multi-label classification. In ICLR, 2024."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013747"},{"key":"e_1_3_2_2_19_1","volume-title":"Inductive Representation Learning on Large Graphs","author":"Hamilton W. L.","year":"2018","unstructured":"W. L. Hamilton, R. Ying, and J. Leskovec. Inductive Representation Learning on Large Graphs, 2018."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_2_23_1","volume-title":"Adaptive Sampling Towards Fast Graph Representation Learning","author":"Huang W.","year":"2018","unstructured":"W. Huang, T. Zhang, Y. Rong, and J. Huang. Adaptive Sampling Towards Fast Graph Representation Learning, 2018."},{"key":"e_1_3_2_2_24_1","volume-title":"Ranking and Other Missing Label Applications. In KDD","author":"Jain H.","year":"2016","unstructured":"H. Jain, Y. Prabhu, and M. Varma. Extreme Multi-label Loss Functions for Recommendation, Tagging, Ranking and Other Missing Label Applications. In KDD, August 2016."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"e_1_3_2_2_26_1","volume-title":"ICML","author":"Jasinska K.","year":"2016","unstructured":"K. Jasinska, K. Dembczynski, R. Busa-Fekete, K. Pfannschmidt, T. Klerx, and E. Hullermeier. Extreme F-measure Maximization using Sparse Probability Estimates. In ICML, 2016."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16974"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_29_1","volume-title":"Bonsai: diverse and shallow trees for extreme multi-label classification. ML","author":"Khandagale S.","year":"2020","unstructured":"S. Khandagale, H. Xiao, and R. Babbar. Bonsai: diverse and shallow trees for extreme multi-label classification. ML, 2020."},{"key":"e_1_3_2_2_30_1","volume-title":"NeurIPS","author":"Kharbanda S.","year":"2022","unstructured":"S. Kharbanda, A. Banerjee, E. Schultheis, and R. Babbar. Cascadexml: Rethinking transformers for end-to-end multi-resolution training in extreme multi-label classification. In NeurIPS, 2022."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1612"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"e_1_3_2_2_34_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Y.","year":"2019","unstructured":"Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_2_36_1","volume-title":"TACL","author":"Luan Y.","year":"2020","unstructured":"Y. Luan, J. Eisenstein, K. Toutanova, and M. Collins. Sparse, Dense, and Attentional Representations for Text Retrieval. In TACL, 2020."},{"key":"e_1_3_2_2_37_1","volume-title":"NeurIPS","author":"Medini T. K. R.","year":"2019","unstructured":"T. K. R. Medini, Q. Huang, Y. Wang, V. Mohan, and A. Shrivastava. Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products. In NeurIPS, 2019."},{"key":"e_1_3_2_2_38_1","volume-title":"NIPS","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean. Distributed Representations of Words and Phrases and Their Compositionality. In NIPS, 2013."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_3"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441807"},{"key":"e_1_3_2_2_41_1","volume-title":"WWW","author":"Mittal A.","year":"2021","unstructured":"A. Mittal, N. Sachdeva, S. Agrawal, S. Agarwal, P. Kar, and M. Varma. ECLARE: Extreme Classification with Label Graph Correlations. In WWW, 2021."},{"key":"e_1_3_2_2_42_1","volume-title":"CVPR","author":"Mittal A.","year":"2022","unstructured":"A. Mittal, K. Dahiya, S. Malani, J. Ramaswamy, S. Kuruvilla, J. Ajmera, K. Chang, S. Agrawal, P. Kar, and M. Varma. Multimodal extreme classification. In CVPR, June 2022."},{"key":"e_1_3_2_2_43_1","volume-title":"ICML","author":"Mohan S.","year":"2015","unstructured":"S. Mohan, D. Saini, A. Mittal, S. R. Chowdhury, B. Paliwal, J. Jiao, M. Gupta, and M. Varma. Enriching Document Representations using Auxiliary Knowledge for Extreme Classification. In ICML, 2015."},{"key":"e_1_3_2_2_44_1","volume-title":"NIPS-W","author":"Paszke A.","year":"2017","unstructured":"A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer. Automatic differentiation in PyTorch. In NIPS-W, 2017."},{"key":"e_1_3_2_2_45_1","volume-title":"WWW","author":"Prabhu Y.","year":"2018","unstructured":"Y. Prabhu, A. Kag, S. Harsola, R. Agrawal, and M. Varma. Parabel: Partitioned label trees for extreme classification with application to dynamic search advertising. In WWW, 2018."},{"key":"e_1_3_2_2_46_1","volume-title":"Rocketqa: An optimized training approach to dense passage retrieval for opendomain question answering","author":"Qu Y.","year":"2021","unstructured":"Y. Qu, Y. Ding, J. Liu, K. Liu, R. Ren, W. X. Zhao, D. Dong, H. Wu, and H. Wang. Rocketqa: An optimized training approach to dense passage retrieval for opendomain question answering, 2021."},{"key":"e_1_3_2_2_47_1","volume-title":"WWW","author":"Saini D.","year":"2021","unstructured":"D. Saini, A.K. Jain, K. Dave, J. Jiao, A. Singh, R. Zhang, and M. Varma. GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification. In WWW, 2021."},{"key":"e_1_3_2_2_48_1","volume-title":"ArXiv","author":"Sanh V.","year":"2019","unstructured":"V. Sanh, L. Debut, J. Chaumond, and T. Wolf. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv, 2019."},{"key":"e_1_3_2_2_49_1","volume-title":"ICML","author":"Siblini W.","year":"2018","unstructured":"W. Siblini, P. Kuntz, and F. Meyer. CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning. In ICML, 2018."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/533"},{"key":"e_1_3_2_2_51_1","volume-title":"NIPS","author":"Wydmuch M.","year":"2018","unstructured":"M. Wydmuch, K. Jasinska, M. Kuznetsov, R. Busa-Fekete, and K. Dembczynski. A no-regret generalization of hierarchical softmax to extreme multi-label classification. In NIPS, 2018."},{"key":"e_1_3_2_2_52_1","volume-title":"ICLR","author":"Xiong L.","year":"2021","unstructured":"L. Xiong, C. Xiong, Y. Li, K.-F. Tang, J. Liu, P. Bennett, J. Ahmed, and A. Overwijk. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In ICLR, 2021."},{"key":"e_1_3_2_2_53_1","first-page":"28798","article-title":"Graphformers: Gnn-nested transformers for representation learning on textual graph","volume":"34","author":"Yang J.","year":"2021","unstructured":"J. Yang, Z. Liu, S. Xiao, C. Li, D. Lian, S. Agrawal, A. Singh, G. Sun, and X. Xie. Graphformers: Gnn-nested transformers for representation learning on textual graph. NeurIPS, 34:28798--28810, 2021.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532009"},{"key":"e_1_3_2_2_55_1","volume-title":"ICML","author":"Ye H.","year":"2020","unstructured":"H. Ye, Z. Chen, D.-H. Wang, and B. .D. Davison. Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification. In ICML, 2020."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098083"},{"key":"e_1_3_2_2_57_1","volume-title":"NeurIPS","author":"You R.","year":"2019","unstructured":"R. You, S. Dai, Z. Zhang, H. Mamitsuka, and S. Zhu. AttentionXML: Extreme MultiLabel Text Classification with Multi-Label Attention Based Recurrent Neural Networks. In NeurIPS, 2019."},{"key":"e_1_3_2_2_58_1","volume-title":"ICLR","author":"Zeng H.","year":"2020","unstructured":"H. Zeng, H. Zhou, A. Srivastava, R. Kannan, and V. Prasanna. GraphSAINT: Graph Sampling Based Inductive Learning Method. In ICLR, 2020."},{"key":"e_1_3_2_2_59_1","volume-title":"NeurIPS","author":"Zhang J.","year":"2021","unstructured":"J. Zhang, W.-c. Chang, H.-f. Yu, and I. Dhillon. Fast multi-resolution transformer fine-tuning for extreme multi-label text classification. In NeurIPS, 2021."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449842"},{"key":"e_1_3_2_2_61_1","volume-title":"Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks","author":"Zou D.","year":"2019","unstructured":"D. Zou, Z. Hu, Y. Wang, S. Jiang, Y. Sun, and Q. Gu. Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks, 2019."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715230","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3715230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T03:07:21Z","timestamp":1759892841000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":61,"alternative-id":["10.1145\/3701716.3715230","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3715230","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}