{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T04:37:46Z","timestamp":1775018266274,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,4,19]]},"DOI":"10.1145\/3442381.3449937","type":"proceedings-article","created":{"date-parts":[[2021,6,3]],"date-time":"2021-06-03T19:24:51Z","timestamp":1622748291000},"page":"3733-3744","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification"],"prefix":"10.1145","author":[{"given":"Deepak","family":"Saini","sequence":"first","affiliation":[{"name":"Microsoft Research, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnav Kumar","family":"Jain","sequence":"additional","affiliation":[{"name":"Microsoft, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kushal","family":"Dave","sequence":"additional","affiliation":[{"name":"Microsoft, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Jiao","sequence":"additional","affiliation":[{"name":"Microsoft, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Singh","sequence":"additional","affiliation":[{"name":"Microsoft, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruofei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manik","family":"Varma","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,6,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"S. Abu-El-Haija B. Perozzi A. Kapoor N. Alipourfard K. Lerman H. Harutyunyan G.\u00a0V. Steeg and A. Galstyan. 2019. MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. arxiv:1905.00067\u00a0[cs.LG]  S. Abu-El-Haija B. Perozzi A. Kapoor N. Alipourfard K. Lerman H. Harutyunyan G.\u00a0V. Steeg and A. Galstyan. 2019. MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. arxiv:1905.00067\u00a0[cs.LG]"},{"key":"e_1_3_2_1_2_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_1_3_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_1_4_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_1_5_1","unstructured":"D. Bahdanau K. Cho and Y. Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473(2014).  D. Bahdanau K. Cho and Y. Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473(2014)."},{"key":"e_1_3_2_1_6_1","unstructured":"K. Bhatia K. Dahiya H. Jain 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 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_1_7_1","doi-asserted-by":"crossref","unstructured":"P. Bojanowski E. Grave A. Joulin and T. Mikolov. 2017. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics (2017).  P. Bojanowski E. Grave A. Joulin and T. Mikolov. 2017. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics (2017).","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_8_1","unstructured":"J. Bruna W. Zaremba A. Szlam and Y. LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203(2013).  J. Bruna W. Zaremba A. Szlam and Y. LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203(2013)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"W.-C. Chang Yu H.-F. K. Zhong Y. Yang and I.-S. Dhillon. 2020. Taming Pretrained Transformers for Extreme Multi-label Text Classification. In KDD.  W.-C. Chang Yu H.-F. K. Zhong Y. Yang and I.-S. Dhillon. 2020. Taming Pretrained Transformers for Extreme Multi-label Text Classification. In KDD.","DOI":"10.1145\/3394486.3403368"},{"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.  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","unstructured":"M. Defferrard X. Bresson and P. Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in neural information processing systems. 3844\u20133852.  M. Defferrard X. Bresson and P. Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in neural information processing systems. 3844\u20133852."},{"key":"e_1_3_2_1_12_1","volume-title":"BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL","author":"Devlin J.","year":"2019","unstructured":"J. Devlin , M.\u00a0 W. Chang , K. Lee , and K. Toutanova . 2019 . BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL (2019). J. Devlin, M.\u00a0W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of The Web Conference","author":"Dey P.","year":"2020","unstructured":"P. Dey , K. Goel , and R. Agrawal . 2020. P-Simrank: Extending Simrank to Scale-Free Bipartite Networks . In Proceedings of The Web Conference 2020 . 3084\u20133090. P. Dey, K. Goel, and R. Agrawal. 2020. P-Simrank: Extending Simrank to Scale-Free Bipartite Networks. In Proceedings of The Web Conference 2020. 3084\u20133090."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of KDD Cup","author":"Gantner Z.","year":"2011","unstructured":"Z. Gantner , L. Drumond , C. Freudenthaler , and L. Schmidt-Thieme . 2012. Personalized ranking for non-uniformly sampled items . In Proceedings of KDD Cup 2011 . 231\u2013247. Z. Gantner, L. Drumond, C. Freudenthaler, and L. Schmidt-Thieme. 2012. Personalized ranking for non-uniformly sampled items. In Proceedings of KDD Cup 2011. 231\u2013247."},{"key":"e_1_3_2_1_15_1","unstructured":"J. Gehring M. Auli D. Grangier and Y.\u00a0N. Dauphin. 2016. A convolutional encoder model for neural machine translation. arXiv preprint arXiv:1611.02344(2016).  J. Gehring M. Auli D. Grangier and Y.\u00a0N. Dauphin. 2016. A convolutional encoder model for neural machine translation. arXiv preprint arXiv:1611.02344(2016)."},{"key":"e_1_3_2_1_16_1","unstructured":"J. Gilmer S.\u00a0S. Schoenholz P.\u00a0F. Riley O. Vinyals and G.\u00a0E. Dahl. 2017. Neural message passing for quantum chemistry. arXiv preprint arXiv:1704.01212(2017).  J. Gilmer S.\u00a0S. Schoenholz P.\u00a0F. Riley O. Vinyals and G.\u00a0E. Dahl. 2017. Neural message passing for quantum chemistry. arXiv preprint arXiv:1704.01212(2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 855\u2013864","author":"Grover A.","unstructured":"A. Grover and J. Leskovec . 2016. node2vec: Scalable feature learning for networks . In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 855\u2013864 . A. Grover and J. Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 855\u2013864."},{"key":"e_1_3_2_1_19_1","unstructured":"W. Hamilton Z. Ying and J. Leskovec. 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems. 1024\u20131034.  W. Hamilton Z. Ying and J. Leskovec. 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems. 1024\u20131034."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778","author":"He K.","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun . 2016. Deep residual learning for image recognition . In Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778 . K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778."},{"key":"e_1_3_2_1_21_1","unstructured":"S. Ioffe and C. Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167(2015).  S. Ioffe and C. Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167(2015)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"e_1_3_2_1_23_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_1_24_1","doi-asserted-by":"crossref","unstructured":"A. Joulin E. Grave P. Bojanowski and T. Mikolov. 2017. Bag of Tricks for Efficient Text Classification. In EACL.  A. Joulin E. Grave P. Bojanowski and T. Mikolov. 2017. Bag of Tricks for Efficient Text Classification. In EACL.","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"S. Khandagale H. Xiao and R. Babbar. 2019. Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification. CoRR (2019).  S. Khandagale H. Xiao and R. Babbar. 2019. Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification. CoRR (2019).","DOI":"10.1007\/s10994-020-05888-2"},{"key":"e_1_3_2_1_26_1","unstructured":"T.\u00a0N. Kipf and M. Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907(2016).  T.\u00a0N. Kipf and M. Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907(2016)."},{"key":"e_1_3_2_1_27_1","unstructured":"T.\u00a0N. Kipf and M. Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. arxiv:1609.02907\u00a0[cs.LG]  T.\u00a0N. Kipf and M. Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. arxiv:1609.02907\u00a0[cs.LG]"},{"key":"e_1_3_2_1_28_1","unstructured":"A. Krizhevsky I. Sutskever and G.\u00a0E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097\u20131105.  A. Krizhevsky I. Sutskever and G.\u00a0E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097\u20131105."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 23rd international conference on World wide web. 85\u201396","author":"Lee J.","unstructured":"J. Lee , S. Bengio , S. Kim , G. Lebanon , and Y. Singer . 2014. Local collaborative ranking . In Proceedings of the 23rd international conference on World wide web. 85\u201396 . J. Lee, S. Bengio, S. Kim, G. Lebanon, and Y. Singer. 2014. Local collaborative ranking. In Proceedings of the 23rd international conference on World wide web. 85\u201396."},{"key":"e_1_3_2_1_31_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.  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_32_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).","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 . 2019 . Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019). Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"W. Lu J. Jiao and R. Zhang. 2020. TwinBERT: Distilling knowledge to twin-structured BERT models for efficient retrieval. arXiv preprint arXiv:2002.06275(2020).  W. Lu J. Jiao and R. Zhang. 2020. TwinBERT: Distilling knowledge to twin-structured BERT models for efficient retrieval. arXiv preprint arXiv:2002.06275(2020).","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_35_1","unstructured":"T.\u00a0K.\u00a0R. 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.\u00a0K.\u00a0R. 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_1_36_1","unstructured":"T. Mikolov K. Chen G. Corrado and J. Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781(2013).  T. Mikolov K. Chen G. Corrado and J. Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781(2013)."},{"key":"e_1_3_2_1_37_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.  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_38_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 . DECAF: Deep Extreme Classification with Label Features. In WSDM. A. Mittal, K. Dahiya, S. Agrawal, D. Saini, S. Agarwal, P. Kar, and M. Varma. 2021. DECAF: Deep Extreme Classification with Label Features. In WSDM."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu269"},{"key":"e_1_3_2_1_40_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. In Advances in neural information processing systems. 8026\u20138037.","author":"Paszke A.","year":"2019","unstructured":"A. Paszke , S. Gross , F. Massa , A. Lerer , J. Bradbury , G. Chanan , T. Killeen , Z. Lin , N. Gimelshein , L. Antiga , 2019 . Pytorch: An imperative style, high-performance deep learning library. In Advances in neural information processing systems. 8026\u20138037. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. In Advances in neural information processing systems. 8026\u20138037."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Y. Prabhu A. Kag S. Gopinath K. Dahiya S. Harsola R. Agrawal and M. Varma. 2018. 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. 2018. 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_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185998"},{"key":"e_1_3_2_1_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_1_44_1","unstructured":"A. Radford J. Wu R. Child D. Luan D. Amodei and I. Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019).  A. Radford J. Wu R. Child D. Luan D. Amodei and I. Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 23rd ACM international conference on conference on information and knowledge management. 101\u2013110","author":"Shen Y.","unstructured":"Y. Shen , X. He , J. Gao , L. Deng , and G. Mesnil . 2014. A latent semantic model with convolutional-pooling structure for information retrieval . In Proceedings of the 23rd ACM international conference on conference on information and knowledge management. 101\u2013110 . Y. Shen, X. He, J. Gao, L. Deng, and G. Mesnil. 2014. A latent semantic model with convolutional-pooling structure for information retrieval. In Proceedings of the 23rd ACM international conference on conference on information and knowledge management. 101\u2013110."},{"key":"e_1_3_2_1_47_1","volume-title":"Learning Semantic Representations Using Convolutional Neural Networks for Web Search. WWW","author":"Shen Y.","year":"2014","unstructured":"Y. Shen , X. He , J. Gao , L. Deng , and G. Mesnil . 2014 . Learning Semantic Representations Using Convolutional Neural Networks for Web Search. WWW 2014 . https:\/\/www.microsoft.com\/en-us\/research\/publication\/learning-semantic-representations-using-convolutional-neural-networks-for-web-search\/ Y. Shen, X. He, J. Gao, L. Deng, and G. Mesnil. 2014. Learning Semantic Representations Using Convolutional Neural Networks for Web Search. WWW 2014. https:\/\/www.microsoft.com\/en-us\/research\/publication\/learning-semantic-representations-using-convolutional-neural-networks-for-web-search\/"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.572108"},{"key":"e_1_3_2_1_49_1","unstructured":"P. Veli\u010dkovi\u0107 G. Cucurull A. Casanova A. Romero P. Li\u00f2 and Y. Bengio. 2018. Graph Attention Networks. arxiv:1710.10903\u00a0[stat.ML]  P. Veli\u010dkovi\u0107 G. Cucurull A. Casanova A. Romero P. Li\u00f2 and Y. Bengio. 2018. Graph Attention Networks. arxiv:1710.10903\u00a0[stat.ML]"},{"key":"e_1_3_2_1_50_1","unstructured":"O. Vinyals M. Fortunato and N. Jaitly. 2015. Pointer networks. In Advances in neural information processing systems. 2692\u20132700.  O. Vinyals M. Fortunato and N. Jaitly. 2015. Pointer networks. In Advances in neural information processing systems. 2692\u20132700."},{"key":"e_1_3_2_1_51_1","unstructured":"K. Xu W. Hu J. Leskovec and S. Jegelka. 2018. How powerful are graph neural networks?arXiv preprint arXiv:1810.00826(2018).  K. Xu W. Hu J. Leskovec and S. Jegelka. 2018. How powerful are graph neural networks?arXiv preprint arXiv:1810.00826(2018)."},{"key":"e_1_3_2_1_52_1","unstructured":"K. Xu C. Li Y. Tian T. Sonobe K. Kawarabayashi and S. Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. arXiv preprint arXiv:1806.03536(2018).  K. Xu C. Li Y. Tian T. Sonobe K. Kawarabayashi and S. Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. arXiv preprint arXiv:1806.03536(2018)."},{"key":"e_1_3_2_1_53_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5753\u20135763.","author":"Yang Z.","year":"2019","unstructured":"Z. Yang , Z. Dai , Y. Yang , J. Carbonell , R. Salakhutdinov , and Q.\u00a0 V. Le . 2019 . Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5753\u20135763. Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. Salakhutdinov, and Q.\u00a0V. Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5753\u20135763."},{"key":"e_1_3_2_1_54_1","unstructured":"E.H.\u00a0I. Yen X. Huang W. Dai I. Ravikumar P.and\u00a0Dhillon and E. Xing. 2017. PPDSparse: A Parallel Primal-Dual Sparse Method for Extreme Classification. In KDD.  E.H.\u00a0I. Yen X. Huang W. Dai I. Ravikumar P.and\u00a0Dhillon and E. Xing. 2017. PPDSparse: A Parallel Primal-Dual Sparse Method for Extreme Classification. In KDD."},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 974\u2013983","author":"Ying R.","unstructured":"R. Ying , R. He , K. Chen , P. Eksombatchai , W.\u00a0 L. Hamilton , and J. Leskovec . 2018. Graph convolutional neural networks for web-scale recommender systems . In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 974\u2013983 . R. Ying, R. He, K. Chen, P. Eksombatchai, W.\u00a0L. Hamilton, and J. Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 974\u2013983."},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (July 2018","author":"Ying R.","year":"1981","unstructured":"R. Ying , R. He , K. Chen , P. Eksombatchai , W.\u00a0 L. Hamilton , and J. Leskovec . 2018. Graph Convolutional Neural Networks for Web-Scale Recommender Systems . Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (July 2018 ). https:\/\/doi.org\/10.1145\/32 1981 9.3219890 R. Ying, R. He, K. Chen, P. Eksombatchai, W.\u00a0L. Hamilton, and J. Leskovec. 2018. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (July 2018). https:\/\/doi.org\/10.1145\/3219819.3219890"},{"key":"e_1_3_2_1_57_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. (2019).  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. (2019)."},{"key":"e_1_3_2_1_58_1","unstructured":"M. Zhang and Y. Chen. 2018. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems. 5165\u20135175.  M. Zhang and Y. Chen. 2018. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems. 5165\u20135175."},{"key":"e_1_3_2_1_59_1","volume-title":"Neural IR Meets Graph Embedding: A Ranking Model for Product Search. In The World Wide Web Conference. 2390\u20132400","author":"Zhang Y.","unstructured":"Y. Zhang , D. Wang , and Y. Zhang . 2019 . Neural IR Meets Graph Embedding: A Ranking Model for Product Search. In The World Wide Web Conference. 2390\u20132400 . Y. Zhang, D. Wang, and Y. Zhang. 2019. Neural IR Meets Graph Embedding: A Ranking Model for Product Search. In The World Wide Web Conference. 2390\u20132400."},{"key":"e_1_3_2_1_60_1","volume-title":"Graph Convolution: A High-Order and Adaptive Approach. arxiv:1706.09916\u00a0[cs.LG]","author":"Zhou Z.","year":"2017","unstructured":"Z. Zhou and X. Li . 2017 . Graph Convolution: A High-Order and Adaptive Approach. arxiv:1706.09916\u00a0[cs.LG] Z. Zhou and X. Li. 2017. Graph Convolution: A High-Order and Adaptive Approach. arxiv:1706.09916\u00a0[cs.LG]"}],"event":{"name":"WWW '21: The Web Conference 2021","location":"Ljubljana Slovenia","acronym":"WWW '21","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the Web Conference 2021"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3442381.3449937","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3442381.3449937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:32Z","timestamp":1750195472000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3442381.3449937"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":60,"alternative-id":["10.1145\/3442381.3449937","10.1145\/3442381"],"URL":"https:\/\/doi.org\/10.1145\/3442381.3449937","relation":{},"subject":[],"published":{"date-parts":[[2021,4,19]]},"assertion":[{"value":"2021-06-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}