研究兴趣

论文共 103 篇作者统计合作学者相似作者

按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Zhe Yuan,Zhewei Wei, Fangrui Lv,Ji-Rong Wen
引用0浏览0EI引用
0
0
引用0浏览0引用
0
0
引用168浏览0EI引用
168
0
Xuwei Xu, Sen Wang, Yudong Chen , Yanping Zheng,Zhewei Wei,Jiajun Liu
引用0浏览0EI引用
0
0
引用0浏览0EI引用
0
0
引用3浏览0EI引用
3
0
Hang Zheng, Luo Wei-liang,Gengmo Zhou, Zhiyuan Zhu, Yifei Yuan,Guolin Ke,Zhewei Wei,Zhifeng Gao
引用0浏览0引用
0
0
加载更多
作者统计
  • 合作者
  • 学生
  • 导师
暂无相似学者,你可以通过学者研究领域进行搜索筛选
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
s PageRank with constant relative error and constant failure probability on undirected graphs. We conduct comprehensive experiments to demonstrate the effectiveness of SetPush. ","authors":[{"email":"hanzhi_wang@ruc.edu.cn","id":"5440ec0edabfae61acc0e93b","name":"Hanzhi Wang","org":"Renmin Univ China, Beijing, Peoples R China","orgs":["Renmin Univ China, Beijing, Peoples R China"]},{"email":"zhewei@ruc.edu.cn","id":"53f43094dabfaee02ac89346","name":"Zhewei Wei","org":"Renmin Univ China, Beijing, Peoples R China","orgs":["Renmin Univ China, Beijing, Peoples R China"]}],"create_time":"2023-07-26T04:53:37.505Z","hashs":{"h1":"esptl","h3":"mst"},"id":"64c09a963fda6d7f06e3e1a7","issn":"2150-8097","num_citation":0,"pages":{"end":"2961","start":"2949"},"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002F1B\u002F61\u002FF5\u002F1B61F5069FFE2751A25EFC4018FFCD8D.pdf","title":"Estimating Single-Node PageRank in $\\tilde{O}\\left(\\min\\{d_t,\n \\sqrt{m}\\}\\right)$ Time","urls":["https:\u002F\u002Fopenalex.org\u002FW4385322312","https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.14778\u002F3611479.3611500","db\u002Fjournals\u002Fcorr\u002Fcorr2307.html#abs-2307-13162","https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2307.13162","http:\u002F\u002Fwww.webofknowledge.com\u002F","https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.13162"],"venue":{"info":{"name":"PROCEEDINGS OF THE VLDB ENDOWMENT"},"issue":"11","volume":"16"},"versions":[{"id":"64c09a963fda6d7f06e3e1a7","sid":"2307.13162","src":"arxiv","year":2023},{"id":"654db36c939a5f4082abbe84","sid":"WOS:001059181900022","src":"wos","year":2023},{"id":"64cc9f083fda6d7f06d7e942","sid":"journals\u002Fcorr\u002Fabs-2307-13162","src":"dblp","year":2023},{"id":"655d8318939a5f40822dbd7a","sid":"10.14778\u002F3611479.3611500","src":"acm","year":2023},{"id":"6579220f939a5f4082e997b2","sid":"W4385322312","src":"openalex","year":2023}],"year":2023},{"abstract":" Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations. Recent GCN models use various residual connection techniques to alleviate the model degradation problem such as over-smoothing and gradient vanishing. Existing residual connection techniques, however, fail to make extensive use of underlying graph structure as in the graph spectral domain, which is critical for obtaining satisfactory results on heterophilic graphs. In this paper, we introduce ClenshawGCN, a GNN model that employs the Clenshaw Summation Algorithm to enhance the expressiveness of the GCN model. ClenshawGCN equips the standard GCN model with two straightforward residual modules: the adaptive initial residual connection and the negative second-order residual connection. We show that by adding these two residual modules, ClenshawGCN implicitly simulates a polynomial filter under the Chebyshev basis, giving it at least as much expressive power as polynomial spectral GNNs. In addition, we conduct comprehensive experiments to demonstrate the superiority of our model over spatial and spectral GNN models. ","authors":[{"id":"64c32e168eff4696a897732b","name":"Yuhe Guo","org":"Renmin University of China","orgid":"5f71b2b11c455f439fe3d913","orgs":["Renmin University of China"]},{"id":"53f43094dabfaee02ac89346","name":"Zhewei Wei","org":"Renmin University of China","orgid":"5f71b2b11c455f439fe3d913","orgs":["Renmin University of China"]}],"create_time":"2022-11-01T13:00:42.892Z","hashs":{"h1":"cgnn"},"id":"63608e4f90e50fcafdee1081","lang":"en","num_citation":3,"pages":{"end":"625","start":"614"},"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002F86\u002FFB\u002F9C\u002F86FB9CAE403D4AF53F7CF89B0E0185AB.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2210.16508"],"title":"Clenshaw Graph Neural Networks","update_times":{"u_a_t":"2022-11-06T00:00:25.399Z","u_c_t":"2024-02-11T07:49:08.238Z"},"urls":["https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599275","db\u002Fconf\u002Fkdd\u002Fkdd2023.html#GuoW23","https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599275","https:\u002F\u002Fkdd.org\u002Fkdd2023\u002Fresearch-track-papers\u002F","https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.16508"],"venue_hhb_id":"5ea1b22bedb6e7d53c00c41b","versions":[{"id":"63608e4f90e50fcafdee1081","sid":"2210.16508","src":"arxiv","year":2022},{"id":"64c35a533fda6d7f06b8c95f","sid":"kdd2023#184","src":"conf_kdd","year":2023},{"id":"64f5616d3fda6d7f06f1ed8c","sid":"conf\u002Fkdd\u002FGuoW23","src":"dblp","year":2023},{"id":"65449230939a5f408212a45d","sid":"10.1145\u002F3580305.3599275","src":"acm","year":2023},{"id":"6578435b939a5f40828b8728","sid":"W4307928447","src":"openalex","vsid":"journals\u002Fcorr","year":2022},{"id":"6392ac4290e50fcafd9f7b40","sid":"journals\u002Fcorr\u002Fabs-2210-16508","src":"dblp","vsid":"journals\u002Fcorr","year":2022},{"id":"64af9a013fda6d7f065a66b0","sid":"kdd2023#165","src":"conf_kdd","vsid":"journals\u002Fcorr","year":2022}],"year":2023},{"abstract":"Predicting p K a values of small molecules has key applications in drug discovery and molecular simulation. However, current methods face challenges in rigorously interpreting experimental data and ensuring thermodynamic consistency between successive p K a values. To address these limitations, we present Uni-p K a , an accurate and reliable p K a prediction framework. Uni-p K a is based on comprehensive free energy modeling of possible molecules in protonation equilibrium. Within this framework, a structural enumerator recovers underlying structures in p K a datapoints, and a neural network serves as a free energy predictor, learning from data rigorously while inherently preserving thermodynamic consistency. Through a pretraining-finetuning strategy utilizing predicted and experimental p K a data, Uni-p K a achieves state-of-the-art accuracy among chemoinformatic methods. Uni-p K a provides a good example of combining chemical principles and machine learning to solve scientific problems.","authors":[{"id":"6442f5b1e3c28ee84cdab308","name":"Hang Zheng","org":"SP Technology (South Korea)","orgid":"61e6a0e0689627346574a2bb","orgs":["SP Technology (South Korea)"]},{"name":"Luo Wei-liang","org":"Massachusetts Institute of Technology","orgid":"62331e350a6eb147dca8a7ec","orgs":["Massachusetts Institute of Technology"]},{"id":"64352fa0f2699869fc1e1a18","name":"Gengmo Zhou","org":"Renmin University of China","orgid":"5f71b2b11c455f439fe3d913","orgs":["Renmin University of China"]},{"name":"Zhiyuan Zhu","org":"SP Technology (South Korea)","orgid":"61e6a0e0689627346574a2bb","orgs":["SP Technology (South Korea)"]},{"name":"Yifei Yuan","org":"SP Technology (South Korea)","orgid":"61e6a0e0689627346574a2bb","orgs":["SP Technology (South Korea)"]},{"id":"5f0d83774c775ed682f316fa","name":"Guolin Ke","org":"Digital Payment Technologies (Canada)","orgs":["Digital Payment Technologies (Canada)"]},{"id":"53f43094dabfaee02ac89346","name":"Zhewei Wei","org":"Renmin University of China","orgid":"5f71b2b11c455f439fe3d913","orgs":["Renmin University of China"]},{"id":"62e8aae4d9f20422f0b8a8e4","name":"Zhifeng Gao","org":"Digital Payment Technologies (Canada)","orgs":["Digital Payment Technologies (Canada)"]}],"create_time":"2024-01-25T20:33:32.67Z","doi":"10.21203\u002Frs.3.rs-3367941\u002Fv1","hashs":{"h1":"uapcp","h3":"ppem"},"id":"657900d7939a5f4082b51f54","keywords":["physically consistent uni-pka prediction","protonation","ensemble"],"num_citation":0,"title":"Uni-pKa: An Accurate and Physically Consistent pKa Prediction through Protonation Ensemble Modeling","urls":["https:\u002F\u002Fopenalex.org\u002FW4387732971","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-3367941\u002Fv1"],"venue":{"info":{"name":"Research Square (Research Square)"}},"versions":[{"id":"657900d7939a5f4082b51f54","sid":"W4387732971","src":"openalex","year":2023}],"year":2023}],"profilePubsTotal":103,"profilePatentsPage":0,"profilePatents":null,"profilePatentsTotal":null,"profilePatentsEnd":false,"profileProjectsPage":1,"profileProjects":{"success":true,"msg":"","data":[{"country":"CN","end_date":{"seconds":1546214400},"fund_amount":210000,"fund_currency":"CNY","id":"60b8beca6023d0724eb56996","project_source":"NSFC","start_date":{"seconds":1451606400},"titles":[{"contents":["支持摘要搜索的数据库多维动态索引技术研究"],"language":"ZH"}]}],"total":1,"log_id":"2cwZpBNTD6DQ4QZ4Ii5HA0UDa8H"},"profileProjectsTotal":0,"newInfo":null,"checkDelPubs":[]}};