{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:47Z","timestamp":1740101747943,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018928","name":"Westlake University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018928","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095552","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Wordreg: Mitigating the Gap between Training and Inference with Worst-Case Drop Regularization"],"prefix":"10.1109","author":[{"given":"Jun","family":"Xia","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310058"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bozhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Tan","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangbin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjie","family":"Xu","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"liu","key":"ref15"},{"key":"ref14","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020","journal-title":"ICLRE"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Towards robust graph neural networks against label noise","year":"2021","author":"xia","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.561"},{"key":"ref19","article-title":"Mole-bert: Rethinking pre-training graph neural networks for molecules","author":"xia","year":"2023","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512156"},{"article-title":"A systematic survey of molecular pre-trained models","year":"2022","author":"xia","key":"ref24"},{"key":"ref23","article-title":"Pretraining graph neural networks for molecular representations: Retrospect and prospect","author":"xia","year":"2022","journal-title":"ICML 2022 2nd AI for Science Workshop"},{"article-title":"Protein language models and structure prediction: Connection and progression","year":"2022","author":"hu","key":"ref25"},{"key":"ref20","article-title":"Tudataset: A collection of benchmark datasets for learning with graphs","author":"morris","year":"0","journal-title":"ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+ 2020)"},{"key":"ref22","article-title":"How powerful are graph neural networks?","author":"xu","year":"2018","journal-title":"ICLRE"},{"key":"ref21","article-title":"Semi-supervised classification with graph convolutional networks","author":"thomas kipf","year":"2017","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009795911987"},{"key":"ref7","article-title":"Fraternal dropout","author":"zolna","year":"2018","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383202"},{"key":"ref4","article-title":"Dropout: a simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475622"},{"key":"ref6","article-title":"Dropout with expectation-linear regularization","author":"ma","year":"2017","journal-title":"ICLRE"},{"key":"ref5","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095552.pdf?arnumber=10095552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:08Z","timestamp":1699902188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095552","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}