{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:10:57Z","timestamp":1775913057187,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["61836013; 61825602"],"award-info":[{"award-number":["61836013; 61825602"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539472","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"1120-1130","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Mask and Reason"],"prefix":"10.1145","author":[{"given":"Xiao","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Shiyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Kai","family":"Su","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Yukuo","family":"Cen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Jiezhong","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Mengdi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan-Dianping Group, Beijing, China"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Meituan-Dianping Group, Beijing, China"}]},{"given":"Yuxiao","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Jie","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Erik Arakelyan Daniel Daza Pasquale Minervini and Michael Cochez. 2021. Complex Query Answering with Neural Link Predictors. In ICLR."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Kurt Bollacker Colin Evans Praveen Paritosh Tim Sturge and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD. 1247--1250.","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_1_3_1","volume-title":"Translating embeddings for modeling multi-relational data. NIPS 26","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. NIPS 26 (2013)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Andrew Carlson Justin Betteridge Bryan Kisiel Burr Settles Estevam R Hruschka and Tom M Mitchell. 2010. Toward an architecture for never-ending language learning. In AAAI.","DOI":"10.1609\/aaai.v24i1.7519"},{"key":"e_1_3_2_1_5_1","unstructured":"William W. Cohen Matthew Siegler and Alex Hofer. 2019. Neural Query Language: A Knowledge Base Query Language for Tensorflow. arXiv:1905.06209"},{"key":"e_1_3_2_1_6_1","volume-title":"Introduction to lattices and order","author":"Davey Brian A","unstructured":"Brian A Davey and Hilary A Priestley. 2002. Introduction to lattices and order, Second Edition. Cambridge university press."},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Xin Dong Evgeniy Gabrilovich Geremy Heitz Wilko Horn Ni Lao Kevin Murphy Thomas Strohmann Shaohua Sun and Wei Zhang. 2014. Knowledge vault: A web-scale approach to probabilistic knowledge fusion. In SIGKDD. 601--610.","DOI":"10.1145\/2623330.2623623"},{"key":"e_1_3_2_1_9_1","volume-title":"Graph Random Neural Network for Semi-Supervised Learning on Graphs. NeurIPS","author":"Feng Wenzheng","year":"2020","unstructured":"Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, and Jie Tang. 2020. Graph Random Neural Network for Semi-Supervised Learning on Graphs. NeurIPS (2020)."},{"key":"e_1_3_2_1_10_1","unstructured":"Octavian Ganea Gary B\u00e9cigneul and Thomas Hofmann. 2018. Hyperbolic neural networks. In NeurIPS. 5345--5355."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Mor Geva Roei Schuster Jonathan Berant and Omer Levy. 2021. Transformer Feed-Forward Layers Are Key-Value Memories. In EMNLP. 5484--5495.","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"e_1_3_2_1_12_1","unstructured":"William L Hamilton Payal Bajaj Marinka Zitnik Dan Jurafsky and Jure Leskovec. 2018. Embedding logical queries on knowledge graphs. In NIPS. 2030--2041."},{"key":"e_1_3_2_1_13_1","volume-title":"arXiv preprint arXiv:2103.13262","author":"He Jiaao","year":"2021","unstructured":"Jiaao He, Jiezhong Qiu, Aohan Zeng, Zhilin Yang, Jidong Zhai, and Jie Tang. 2021. Fastmoe:Afast mixture-of-expert training system. arXiv preprint arXiv:2103.13262 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_15_1","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. NeurIPS 33 (2020), 22118--22133.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_16_1","unstructured":"WHu B Liu J Gomes M Zitnik P Liang V Pande and J Leskovec. 2020. Strategies For Pre-training Graph Neural Networks. In ICLR."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"e_1_3_2_1_18_1","unstructured":"Ziniu Hu Yuxiao Dong Kuansan Wang and Yizhou Sun. 2020. Heterogeneous graph transformer. In WWW. 2704--2710."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-9540-7"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16630"},{"key":"e_1_3_2_1_21_1","unstructured":"Dmitry Lepikhin HyoukJoong Lee Yuanzhong Xu Dehao Chen Orhan Firat Yanping Huang Maxim Krikun Noam Shazeer and Zhifeng Chen. 2020. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In ICLR."},{"key":"e_1_3_2_1_22_1","volume-title":"Self-supervised learning: Generative or contrastive","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, ZhaoyuWang, Jing Zhang, and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering (2021)."},{"key":"e_1_3_2_1_23_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. DecoupledWeight Decay Regularization. arXiv:1711.05101 [cs.LG]"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"e_1_3_2_1_25_1","unstructured":"Meng Qu Junkun Chen Louis-Pascal Xhonneux Yoshua Bengio and Jian Tang. 2020. RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs. In ICLR."},{"key":"e_1_3_2_1_26_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu, et al. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140 (2020), 1--67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_27_1","volume-title":"SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs. arXiv preprint arXiv:2110.14890","author":"Ren Hongyu","year":"2021","unstructured":"Hongyu Ren, Hanjun Dai, Bo Dai, Xinyun Chen, Denny Zhou, Jure Leskovec, and Dale Schuurmans. 2021. SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs. arXiv preprint arXiv:2110.14890 (2021)."},{"key":"e_1_3_2_1_28_1","unstructured":"Hongyu Ren Weihua Hu and Jure Leskovec. 2019. Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings. In ICLR."},{"key":"e_1_3_2_1_29_1","unstructured":"Hongyu Ren and Jure Leskovec. 2020. Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_30_1","volume-title":"Pattern classification using ensemble methods","author":"Rokach Lior","unstructured":"Lior Rokach. 2010. Pattern classification using ensemble methods. Vol. 75. World Scientific."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Apoorv Saxena Adrian Kochsiek and Rainer Gemulla. 2022. Sequence-to- Sequence Knowledge Graph Completion and Question Answering. In ACL. 2814--2828.","DOI":"10.18653\/v1\/2022.acl-long.201"},{"key":"e_1_3_2_1_32_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"key":"e_1_3_2_1_34_1","volume-title":"Fernando Pereira, and William W Cohen.","author":"Sun Haitian","year":"2020","unstructured":"Haitian Sun, Andrew Arnold, Tania Bedrax Weiss, Fernando Pereira, and William W Cohen. 2020. Faithful Embeddings for Knowledge Base Queries. NIPS 33 (2020)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_36_1","volume-title":"ICML","volume":"48","author":"Trouillon Th\u00e9o","year":"2016","unstructured":"Th\u00e9o Trouillon, Johannes Welbl, Sebastian Riedel, \u00c9ric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In ICML, Vol. 48."},{"key":"e_1_3_2_1_37_1","unstructured":"Shikhar Vashishth Soumya Sanyal Vikram Nitin and Partha Talukdar. 2019. Composition-based Multi-Relational Graph Convolutional Networks. In ICLR."},{"key":"e_1_3_2_1_38_1","volume-title":"Attention is all you need. NIPS 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. NIPS 30 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Luke Vilnis Xiang Li Shikhar Murty and Andrew McCallum. 2018. Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures. arXiv:1805.06627","DOI":"10.18653\/v1\/P18-1025"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Robert West Evgeniy Gabrilovich Kevin Murphy Shaohua Sun Rahul Gupta and Dekang Lin. 2014. Knowledge base completion via search-based question answering. In WWW. 515--526.","DOI":"10.1145\/2566486.2568032"},{"key":"e_1_3_2_1_42_1","unstructured":"Ruibin Xiong Yunchang Yang Di He Kai Zheng Shuxin Zheng Chen Xing Huishuai Zhang Yanyan Lan Liwei Wang and Tieyan Liu. 2020. On layer normalization in the transformer architecture. In ICML. PMLR 10524--10533."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Wenhan Xiong Thien Hoang and William Yang Wang. 2017. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning. In EMNLP. 564--573.","DOI":"10.18653\/v1\/D17-1060"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_45_1","volume-title":"Do Transformers Really Perform Badly for Graph Representation? NeurIPS 34","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do Transformers Really Perform Badly for Graph Representation? NeurIPS 34 (2021)."},{"key":"e_1_3_2_1_46_1","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. NeurIPS 33 (2020), 5812--5823.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_47_1","volume-title":"Graph transformer networks. NeurIPS 32","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. NeurIPS 32 (2019)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330785"},{"key":"e_1_3_2_1_49_1","volume-title":"MoEfication: Conditional Computation of Transformer Models for Efficient Inference. arXiv preprint arXiv:2110.01786","author":"Zhang Zhengyan","year":"2021","unstructured":"Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, and Jie Zhou. 2021. MoEfication: Conditional Computation of Transformer Models for Efficient Inference. arXiv preprint arXiv:2110.01786 (2021)."},{"key":"e_1_3_2_1_50_1","unstructured":"Difan Zou Ziniu Hu Yewen Wang Song Jiang Yizhou Sun and Quanquan Gu. 2019. Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks. arXiv:1911.07323"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539472","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:03:03Z","timestamp":1750186983000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539472"}},"subtitle":["Pre-Training Knowledge Graph Transformers for Complex Logical Queries"],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":50,"alternative-id":["10.1145\/3534678.3539472","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539472","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}