{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T21:54:08Z","timestamp":1778622848828,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":63,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF1201300"],"award-info":[{"award-number":["2021YFF1201300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872216, T2125007, 31900862"],"award-info":[{"award-number":["61872216, T2125007, 31900862"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539426","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"857-867","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["KPGT"],"prefix":"10.1145","author":[{"given":"Han","family":"Li","sequence":"first","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"given":"Dan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"given":"Jianyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2017. Tox21 Challenge. (2017). http:\/\/tripod.nih.gov\/tox21\/challenge\/"},{"key":"e_1_3_2_2_2_1","volume-title":"Deep Learning using Rectified Linear Units (ReLU). CoRR","author":"Agarap Abien Fred","year":"2018","unstructured":"Abien Fred Agarap. 2018. Deep Learning using Rectified Linear Units (ReLU). CoRR, Vol. abs\/1803.08375 (2018)."},{"key":"e_1_3_2_2_3_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Lei Jimmy","year":"2016","unstructured":"Lei Jimmy Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. CoRR (2016)."},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. PMLR, 748--758","author":"Beaini Dominique","year":"2021","unstructured":"Dominique Beaini, Saro Passaro, Vincent L\u00e9tourneau, Will Hamilton, Gabriele Corso, and Pietro Li\u00f2. 2021. Directional graph networks. In International Conference on Machine Learning. PMLR, 748--758."},{"key":"e_1_3_2_2_5_1","volume-title":"Nature","volume":"559","author":"Butler Keith T","year":"2018","unstructured":"Keith T Butler, Daniel W Davies, Hugh Cartwright, Olexandr Isayev, and Aron Walsh. 2018. Machine learning for molecular and materials science. Nature, Vol. 559, 7715 (2018), 547--555."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2014.08.005"},{"key":"e_1_3_2_2_7_1","volume-title":"Jaakkola","author":"Chen Benson","year":"2019","unstructured":"Benson Chen, Regina Barzilay, and Tommi S. Jaakkola. 2019. Path-Augmented Graph Transformer Network. CoRR, Vol. abs\/1905.12712 (2019)."},{"key":"e_1_3_2_2_8_1","volume-title":"NeurIPS","author":"Corso Gabriele","year":"2020","unstructured":"Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Li\u00f2, and Petar Velickovic. 2020. Principal Neighbourhood Aggregation for Graph Nets. In NeurIPS 2020."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci034243x"},{"key":"e_1_3_2_2_10_1","first-page":"4171","article-title":"BERT","volume":"2019","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-HLT 2019. 4171--4186.","journal-title":"Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0283-x"},{"key":"e_1_3_2_2_12_1","first-page":"1","article-title":"Beyond english-centric multilingual machine translation","volume":"22","author":"Fan Angela","year":"2021","unstructured":"Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, et almbox. 2021. Beyond english-centric multilingual machine translation. Journal of Machine Learning Research, Vol. 22, 107 (2021), 1--48.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_3_2_2_14_1","volume-title":"mbox","author":"Anna Gaulton","year":"2017","unstructured":"Anna Gaulton et almbox. 2017. The ChEMBL database in 2017. Nucleic acids research, Vol. 45, D1 (2017), D945--D954."},{"key":"e_1_3_2_2_15_1","volume-title":"Shaun McGlinchey, David Michalovich, Bissan Al-Lazikani, et al.","author":"Gaulton Anna","year":"2012","unstructured":"Anna Gaulton, Louisa J Bellis, A Patricia Bento, Jon Chambers, Mark Davies, Anne Hersey, Yvonne Light, Shaun McGlinchey, David Michalovich, Bissan Al-Lazikani, et al. 2012. ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic acids research, Vol. 40, D1 (2012), D1100-D1107."},{"key":"e_1_3_2_2_16_1","volume-title":"A data-driven approach to predicting successes and failures of clinical trials. Cell chemical biology","author":"Gayvert Kaitlyn M","year":"2016","unstructured":"Kaitlyn M Gayvert, Neel S Madhukar, and Olivier Elemento. 2016. A data-driven approach to predicting successes and failures of clinical trials. Cell chemical biology, Vol. 23, 10 (2016), 1294--1301."},{"key":"e_1_3_2_2_17_1","volume-title":"International conference on machine learning. PMLR, 1263--1272","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263--1272."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5589557"},{"key":"e_1_3_2_2_20_1","volume-title":"NeurIPS","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In NeurIPS 2017. 1024--1034."},{"key":"e_1_3_2_2_21_1","volume-title":"2021 a. Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377","author":"He Kaiming","year":"2021","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. 2021 a. Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"Piotr Doll\u00e1 r, and Ross B. Girshick. 2021 b. Masked Autoencoders Are Scalable Vision Learners. CoRR","author":"He Kaiming","year":"2021","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1 r, and Ross B. Girshick. 2021 b. Masked Autoencoders Are Scalable Vision Learners. CoRR, Vol. abs\/2111.06377 (2021)."},{"key":"e_1_3_2_2_23_1","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning. In CVPR","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In CVPR 2020. 9726--9735."},{"key":"e_1_3_2_2_24_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_2_25_1","volume-title":"Strategies for Pre-training Graph Neural Networks. In ICLR","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay S. Pande, and Jure Leskovec. 2020. Strategies for Pre-training Graph Neural Networks. In ICLR 2020."},{"key":"e_1_3_2_2_26_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_2_28_1","volume-title":"NeurIPS 2021","volume":"34","author":"Kreuzer Devin","year":"2021","unstructured":"Devin Kreuzer, Dominique Beaini, Will Hamilton, Vincent L\u00e9tourneau, and Prudencio Tossou. 2021. Rethinking graph transformers with spectral attention. NeurIPS 2021, Vol. 34 (2021)."},{"key":"e_1_3_2_2_29_1","volume-title":"Lars Juhl Jensen, and Peer Bork","author":"Kuhn Michael","year":"2016","unstructured":"Michael Kuhn, Ivica Letunic, Lars Juhl Jensen, and Peer Bork. 2016. The SIDER database of drugs and side effects. Nucleic acids research, Vol. 44, D1 (2016), D1075--D1079."},{"key":"e_1_3_2_2_30_1","volume-title":"ICML","author":"Li Xilai","year":"2019","unstructured":"Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher, and Caiming Xiong. 2019. Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting. In ICML 2019. PMLR, 3925--3934."},{"key":"e_1_3_2_2_31_1","volume-title":"Mehmet Furkan Demirel, and Yingyu Liang","author":"Liu Shengchao","year":"2019","unstructured":"Shengchao Liu, Mehmet Furkan Demirel, and Yingyu Liang. 2019. N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules. In NeurIPS 2019. 8464--8476."},{"key":"e_1_3_2_2_32_1","volume-title":"2021 b. Pre-training Molecular Graph Representation with 3D Geometry. arXiv preprint arXiv:2110.07728","author":"Liu Shengchao","year":"2021","unstructured":"Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, and Jian Tang. 2021 b. Pre-training Molecular Graph Representation with 3D Geometry. arXiv preprint arXiv:2110.07728 (2021)."},{"key":"e_1_3_2_2_33_1","volume-title":"2021 a. Swin Transformer V2: Scaling Up Capacity and Resolution. arXiv preprint arXiv:2111.09883","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, et al. 2021 a. Swin Transformer V2: Scaling Up Capacity and Resolution. arXiv preprint arXiv:2111.09883 (2021)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci300124c"},{"key":"e_1_3_2_2_35_1","volume-title":"Molecule Attention Transformer. CoRR","author":"Maziarka Lukasz","year":"2020","unstructured":"Lukasz Maziarka, Tomasz Danel, Slawomir Mucha, Krzysztof Rataj, Jacek Tabor, and Stanislaw Jastrzebski. 2020. Molecule Attention Transformer. CoRR, Vol. abs\/2002.08264 (2020)."},{"key":"e_1_3_2_2_36_1","volume-title":"Graphit: Encoding graph structure in transformers. arXiv preprint arXiv:2106.05667","author":"Mialon Gr\u00e9goire","year":"2021","unstructured":"Gr\u00e9goire Mialon, Dexiong Chen, Margot Selosse, and Julien Mairal. 2021. Graphit: Encoding graph structure in transformers. arXiv preprint arXiv:2106.05667 (2021)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-014-9747-x"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0258-y"},{"key":"e_1_3_2_2_39_1","unstructured":"Adam Paszke et al. 2017. Automatic differentiation in PyTorch. In NIPS-W."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms19041040"},{"key":"e_1_3_2_2_41_1","volume-title":"Deep Learning for the Life Sciences","author":"Ramsundar Bharath","unstructured":"Bharath Ramsundar, Peter Eastman, Patrick Walters, Vijay Pande, Karl Leswing, and Zhenqin Wu. 2019. Deep Learning for the Life Sciences. O'Reilly Media."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Ann M Richard et al. 2016. ToxCast chemical landscape: paving the road to 21st century toxicology. Chemical research in toxicology Vol. 29 8 (2016) 1225--1251.","DOI":"10.1021\/acs.chemrestox.6b00135"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"e_1_3_2_2_44_1","volume-title":"Wenbinn Neg Huang, and Junzhou Huang","author":"Rong Yu","year":"2020","unstructured":"Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbinn Neg Huang, and Junzhou Huang. 2020. Self-Supervised Graph Transformer on Large-Scale Molecular Data. IurIPS 2020."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"e_1_3_2_2_46_1","volume-title":"3D Infomax improves GNNs for Molecular Property Prediction. arXiv preprint arXiv:2110.04126","author":"St\u00e4rk Hannes","year":"2021","unstructured":"Hannes St\u00e4rk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan G\u00fcnnemann, and Pietro Li\u00f2. 2021. 3D Infomax improves GNNs for Molecular Property Prediction. arXiv preprint arXiv:2110.04126 (2021)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00290"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17844-8"},{"key":"e_1_3_2_2_49_1","volume-title":"ADMET in silico modelling: towards prediction paradise? Nature reviews Drug discovery","author":"De Waterbeemd Han Van","year":"2003","unstructured":"Han Van De Waterbeemd and Eric Gifford. 2003. ADMET in silico modelling: towards prediction paradise? Nature reviews Drug discovery, Vol. 2, 3 (2003), 192--204."},{"key":"e_1_3_2_2_50_1","volume-title":"NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS 2017. 5998--6008."},{"key":"e_1_3_2_2_51_1","volume-title":"Deep Graph Infomax. In ICLR","author":"Velickovic Petar","year":"2019","unstructured":"Petar Velickovic, William Fedus, William L. Hamilton, Pietro Li\u00f2, Yoshua Bengio, and R. Devon Hjelm. 2019. Deep Graph Infomax. In ICLR 2019. OpenReview.net."},{"key":"e_1_3_2_2_52_1","unstructured":"Minjie Wang et al. 2019. Deep Graph Library: A Graph-Centric Highly-Performant Package for Graph Neural Networks. arXiv preprint arXiv:1909.01315 (2019)."},{"key":"e_1_3_2_2_53_1","volume-title":"MolCLR: molecular contrastive learning of representations via graph neural networks. arXiv preprint arXiv:2102.10056","author":"Wang Yuyang","year":"2021","unstructured":"Yuyang Wang, Jianren Wang, Zhonglin Cao, and Amir Barati Farimani. 2021. MolCLR: molecular contrastive learning of representations via graph neural networks. arXiv preprint arXiv:2102.10056 (2021)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.11.009"},{"key":"e_1_3_2_2_55_1","volume-title":"MoleculeNet: a benchmark for molecular machine learning. Chemical science","author":"Wu Zhenqin","year":"2018","unstructured":"Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. 2018. MoleculeNet: a benchmark for molecular machine learning. Chemical science, Vol. 9, 2 (2018), 513--530."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00959"},{"key":"e_1_3_2_2_57_1","volume-title":"ICLR","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR 2019."},{"key":"e_1_3_2_2_58_1","volume-title":"Self-supervised Graph-level Representation Learning with Local and Global Structure. In ICML","volume":"139","author":"Xu Minghao","year":"2021","unstructured":"Minghao Xu, Hang Wang, Bingbing Ni, Hongyu Guo, and Jian Tang. 2021. Self-supervised Graph-level Representation Learning with Local and Global Structure. In ICML 2021, Vol. 139. 11548--11558."},{"key":"e_1_3_2_2_59_1","volume-title":"Molecular descriptors in chemoinformatics, computational combinatorial chemistry, and virtual screening. Combinatorial chemistry & high throughput screening","author":"Xue Ling","year":"2000","unstructured":"Ling Xue and Jurgen Bajorath. 2000. Molecular descriptors in chemoinformatics, computational combinatorial chemistry, and virtual screening. Combinatorial chemistry & high throughput screening, Vol. 3, 5 (2000), 363--372."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"e_1_3_2_2_61_1","volume-title":"NeurIPS","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?. In NeurIPS 2021."},{"key":"e_1_3_2_2_62_1","volume-title":"Graph Contrastive Learning Automated. In ICML","volume":"139","author":"You Yuning","year":"2021","unstructured":"Yuning You, Tianlong Chen, Yang Shen, and Zhangyang Wang. 2021. Graph Contrastive Learning Automated. In ICML 2021, Vol. 139. 12121--12132."},{"key":"e_1_3_2_2_63_1","volume-title":"NeurIPS","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. In NeurIPS 2020."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"}],"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\/3534678.3539426","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539426","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\/3534678.3539426"}},"subtitle":["Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction"],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":63,"alternative-id":["10.1145\/3534678.3539426","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539426","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"}}]}}