Search

Your search keyword '"Zhou, Zhiming"' showing total 1,493 results
Start Over Author "Zhou, Zhiming"
1,493 results on '"Zhou, Zhiming"'

1. Residual Multi-Task Learner for Applied Ranking

Author

Fu, Cong, Wang, Kun, Wu, Jiahua, Chen, Yizhou, Huzhang, Guangda, Ni, Yabo, Zeng, Anxiang, and Zhou, Zhiming

Subjects
Computer Science - Information Retrieval, Computer Science - Machine Learning
Abstract

Modern e-commerce platforms rely heavily on modeling diverse user feedback to provide personalized services. Consequently, multi-task learning has become an integral part of their ranking systems. However, existing multi-task learning methods encounter two main challenges: some lack explicit modeling of task relationships, resulting in inferior performance, while others have limited applicability due to being computationally intensive, having scalability issues, or relying on strong assumptions. To address these limitations and better fit our real-world scenario, pre-rank in Shopee Search, we introduce in this paper ResFlow, a lightweight multi-task learning framework that enables efficient cross-task information sharing via residual connections between corresponding layers of task networks. Extensive experiments on datasets from various scenarios and modalities demonstrate its superior performance and adaptability over state-of-the-art methods. The online A/B tests in Shopee Search showcase its practical value in large-scale industrial applications, evidenced by a 1.29% increase in OPU (order-per-user) without additional system latency. ResFlow is now fully deployed in the pre-rank module of Shopee Search. To facilitate efficient online deployment, we propose a novel offline metric Weighted Recall@K, which aligns well with our online metric OPU, addressing the longstanding online-offline metric misalignment issue. Besides, we propose to fuse scores from the multiple tasks additively when ranking items, which outperforms traditional multiplicative fusion. The code is released at https://github.com/BrunoTruthAlliance/ResFlow

Published
2024

8. Recurrent Temporal Revision Graph Networks

Author

Chen, Yizhou, Zeng, Anxiang, Huzhang, Guangda, Yu, Qingtao, Zhang, Kerui, Yuanpeng, Cao, Wu, Kangle, Yu, Han, and Zhou, Zhiming

Subjects
Computer Science - Machine Learning, Computer Science - Social and Information Networks
Abstract

Temporal graphs offer more accurate modeling of many real-world scenarios than static graphs. However, neighbor aggregation, a critical building block of graph networks, for temporal graphs, is currently straightforwardly extended from that of static graphs. It can be computationally expensive when involving all historical neighbors during such aggregation. In practice, typically only a subset of the most recent neighbors are involved. However, such subsampling leads to incomplete and biased neighbor information. To address this limitation, we propose a novel framework for temporal neighbor aggregation that uses the recurrent neural network with node-wise hidden states to integrate information from all historical neighbors for each node to acquire the complete neighbor information. We demonstrate the superior theoretical expressiveness of the proposed framework as well as its state-of-the-art performance in real-world applications. Notably, it achieves a significant +9.6% improvement on averaged precision in a real-world Ecommerce dataset over existing methods on 2-layer models.

Published
2023

9. Changing-look Active Galactic Nuclei from the Dark Energy Spectroscopic Instrument. I.Sample from the Early Data

Author

Guo, Wei-Jian, Zou, Hu, Fawcett, Victoria Anne, Canning, Rebecca, Juneau, Stephanie, Davis, Tamara M., Alexander, David M., Jiang, Linhua, Aguilar, Jessica Nicole, Ahlen, Steven, Brooks, David, Claybaugh, Todd, de la Macorra, Axel, Doel, Peter, Fanning, Kevin, Forero-Romero, Jaime E., Gontcho, Satya Gontcho A, Honscheid, Klaus, Kisner, Theodore, Kremin, Anthony, Landriau, Martin, Meisner, Aaron, Miquel, Ramon, Moustakas, John, Nie, Jundan, Pan, Zhiwei, Poppett, Claire, Prada, Francisco, Rezaie, Mehdi, Rossi, Graziano, Siudek, Małgorzata, Sanchez, Eusebio, Schubnell, Michael, Seo, Hee-Jong, Sui, Jipeng, Tarlé, Gregory, and Zhou, Zhiming

Subjects
Astrophysics - Astrophysics of Galaxies
Abstract

Changing-look Active Galactic Nuclei (CL AGN) can be generally confirmed by the emergence (turn-on) or disappearance (turn-off) of broad emission lines, associated with a transient timescale (about $100\sim5000$ days) that is much shorter than predicted by traditional accretion disk models. We carry out a systematic CL AGN search by cross-matching the spectra coming from the Dark Energy Spectroscopic Instrument and the Sloan Digital Sky Survey. Following previous studies, we identify CL AGN based on $\rm{H}\alpha $, $\rm{H}\beta$, and Mg\,{\sc ii} at $z\leq0.75$ and Mg\,{\sc ii}, C\,{\sc iii}], and C\,{\sc iv} at $z>0.75$. We present 130 CL AGN based on visual inspection and three selection criteria, including 2 $\rm{H}\alpha$, 45 $\rm{H}\beta$, 38 Mg\,{\sc ii}, 61 C\,{\sc iii}], and 10 C\,{\sc iv} CL AGN. Twenty cases show simultaneous appearances/disappearances of two broad emission lines while three AGN exhibit the concurrent appearance of three broad emission lines. We also present 91 CL AGN candidates with significant flux variation of broad emission lines but remaining strong broad components. In the confirmed CL AGN, 42 cases show additional CL candidate features for different lines. In this paper, we find 1) a 95:35 ratio of a turn-on to turn-off CL AGN; 2) the highest redshift CL AGN ($z=3.56$) ever discovered; 3) an upper limit transition timescale ranging from 244 to 5762 days in the rest-frame; 4) the majority of CL AGN follow the bluer-when-brighter trend. Our results greatly increase the current CL census ($30\sim50\%$) and would be conducive to explore the underlying physical mechanism.

Published
2023

10. Learning to Branch in Combinatorial Optimization with Graph Pointer Networks

Author

Wang, Rui, Zhou, Zhiming, Zhang, Tao, Wang, Ling, Xu, Xin, Liao, Xiangke, and Li, Kaiwen

Subjects
Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Mathematics - Combinatorics
Abstract

Branch-and-bound is a typical way to solve combinatorial optimization problems. This paper proposes a graph pointer network model for learning the variable selection policy in the branch-and-bound. We extract the graph features, global features and historical features to represent the solver state. The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions. The model is trained to imitate the classic strong branching expert rule by a designed top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. Our approach also outperforms the state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

Published
2023

11. Clustered Embedding Learning for Recommender Systems

Author

Chen, Yizhou, Huzhang, Guangda, Zeng, Anxiang, Yu, Qingtao, Sun, Hui, Li, Heng-yi, Li, Jingyi, Ni, Yabo, Yu, Han, and Zhou, Zhiming

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

In recent years, recommender systems have advanced rapidly, where embedding learning for users and items plays a critical role. A standard method learns a unique embedding vector for each user and item. However, such a method has two important limitations in real-world applications: 1) it is hard to learn embeddings that generalize well for users and items with rare interactions on their own; and 2) it may incur unbearably high memory costs when the number of users and items scales up. Existing approaches either can only address one of the limitations or have flawed overall performances. In this paper, we propose Clustered Embedding Learning (CEL) as an integrated solution to these two problems. CEL is a plug-and-play embedding learning framework that can be combined with any differentiable feature interaction model. It is capable of achieving improved performance, especially for cold users and items, with reduced memory cost. CEL enables automatic and dynamic clustering of users and items in a top-down fashion, where clustered entities jointly learn a shared embedding. The accelerated version of CEL has an optimal time complexity, which supports efficient online updates. Theoretically, we prove the identifiability and the existence of a unique optimal number of clusters for CEL in the context of nonnegative matrix factorization. Empirically, we validate the effectiveness of CEL on three public datasets and one business dataset, showing its consistently superior performance against current state-of-the-art methods. In particular, when incorporating CEL into the business model, it brings an improvement of $+0.6\%$ in AUC, which translates into a significant revenue gain; meanwhile, the size of the embedding table gets $2650$ times smaller.

Published
2023

14. Research on Autonomous Decision-Making of Multi-UAV Air Combat Based on Deep Reinforcement Learning

Author

Zhou, Zhiming, Qi, Hongmin, Liu, Zhen, Qian, Dianwei, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Li, Xiaoduo, editor, Song, Xun, editor, and Zhou, Yingjiang, editor

Published
2024
Full Text
View/download PDF

23. Mechanism of LDH and IL-8 involved in pancreatic cancer pain and the correlation of pain degree

Author

Zhou Zhiming, Guo Zongfeng, Lu Xiaomin, and Xu Xiaoqing

Subjects
lactate dehydrogenase, interleukin 8, pain, pancreatic cancer, mechanism, Biochemistry, QD415-436
Abstract

Background: This research aimed to observe the mechanism of lactate dehydrogenase (LDH) and interleukin 8 (IL8) in pancreatic cancer pain and their correlation with pain degree. Methods: 126 patients with pancreatic cancer who visited our hospital from January 2021 to February 2023 were selected. The patients were divided into groups of 58 patients with low pain (1~3 points) and 68 patients with high pain (4~10 points) by visual analog scale (VAS). And 50 health examinees in the same period were selected as the healthy control group. The serum LDH and IL-8 concentrations are analyzed by enzyme-linked immunosorbent assay, and the subjective pain grading method score is analyzed. The differences in LDH and IL-8 concentrations among the three groups of patients were compared. Pearson correlation analysis was used to investigate the correlation between LDH, IL-8 concentrations, and patient pain. Binary logistic regression was used to determine independent risk factors for high pain, and ROC curves were used to analyze the diagnostic efficacy of each indicator. Results: The serum LDH and IL-8 concentrations in the high-pain group were exceed the low-pain group's (P190 U/L, IL-8 is >36 pg/mL, and the relevant standards for prediction models are >5.75. Conclusions: LDH and IL-8 participate in the pain aggravation process of pancreatic cancer and are closely related to the pain grading. The combination of LDH and IL-8 can be used as a biological indicator to evaluate the pain severity of pancreatic cancer and provide a reference for clinical diagnosis and treatment.

Published
2024
Full Text
View/download PDF

24. Lowering systolic blood pressure to less than 120 mm Hg versus less than 140 mm Hg in patients with high cardiovascular risk with and without diabetes or previous stroke: an open-label, blinded-outcome, randomised trial

Author

Ai, Xinyue, An, Chun, An, Yuhong, Bai, Shiru, Bai, Xueke, Bi, Jingao, Bin, Xiaoling, Bu, Miaomiao, Bu, Peili, Bu, Wei, Cai, Lvping, Cai, Nana, Cai, Shuhui, Cai, Ting, Cai, Wenjing, Cao, Bin, Cao, Bingbing, Cao, Huaping, Cao, Libo, Cao, Xiancun, Chai, Hui, Chai, Yonggui, Chai, Zhiyong, Chang, Chunduo, Chang, Jianbao, Chang, Shuyue, Chang, Yunling, Chao, Huanhuan, Che, Hang, Che, Qianqiu, Chen, Danlin, Chen, Dongsheng, Chen, Faxiu, Chen, Guang, Chen, Hairong, Chen, Hao, Chen, Huahua, Chen, Huijun, Chen, Jiafu, Chen, Jian, Chen, Jiasen, Chen, Jing, Chen, Jinzi, Chen, Junrong, Chen, lichun, Chen, Lijuan, Chen, Liyuan, Chen, Qun, Chen, Run, Chen, Shaoxing, Chen, Song, Chen, Tieshuang, Chen, Xianghong, Chen, Xiaowu, Chen, Xudong, Chen, Xue, Chen, Xunchun, Chen, Yao, Chen, Yongli, Chen, Yuanyue, Chen, Yuhong, Chen, Yuyi, Chen, Zhangying, Chen, Zhidong, Chen, Zuyi, Cheng, Caiming, Cheng, Jianbin, Cheng, Xiaoxia, Chu, Junjie, Cui, Ruifeng, Cui, Xiaolin, Cui, Xuechen, Cui, Yang, Cui, Zhonghua, Dai, Wanhong, Dai, Xing, Ding, Chunxia, Ding, Huihong, Ding, Qiuhong, Ding, Yaozong, Ding, Yingjie, Dong, Jiajia, Dong, Lei, Dong, Qi, Dong, Yumei, Du, Bing, Du, Hong, Du, Jie, Du, Laijing, Du, Meiling, Du, Qiong, Du, Tianmin, Du, Xue, Duan, Ru, Duan, Xiaojing, Duan, Xiaoting, Fan, Dandan, Fan, Xiaohong, Fan, Xin, Fang, Fang, Fang, Jing, Fang, Xibo, Fang, Yang, Feng, Erke, Feng, Hejin, Feng, Ling, Feng, Rui, Feng, Zhaohui, Fu, Hongmei, Fu, Qiuai, Gao, Haofei, Gao, Li, Gao, Lina, Gao, Liwei, Gao, Lu, Gao, Min, Gao, Qian, Gao, Yan, Gao, Yuan, Ge, Jinzhuo, Geng, Hongxu, Geng, Hui, Geng, Leijun, Geng, Lianqing, Gou, Hongyan, Gu, Qin, Guan, Lili, Guan, Shuo, Guan, Wenchi, Guan, Zheng, Guang, Bin, Guo, Anran, Guo, Changhong, Guo, Gaofeng, Guo, Lizhi, Guo, Qing, Guo, Qiue, Guo, Ying, Guo, Zhihua, Han, Aihong, Han, Meihong, Han, Suhui, Han, Xinru, Han, Yajun, Hao, Feng, Hao, Jingmin, Hao, Shiguo, He, Chuanhui, He, Dejian, He, Mengyuan, He, Miaomiao, He, Shaojuan, He, Wenkai, He, Xiaoyu, He, Yuxiang, Hong, Jige, Hou, Chuanxing, Hou, Jing, Hu, Danli, Hu, Jian, Hu, Jun, Hu, Lingai, Hu, Mengying, Hu, Zhiyuan, Huang, Anhui, Huang, Chunxia, Huang, Haolin, Huang, Jianlan, Huang, Sha, Huang, Siqi, Huang, Weijun, Huang, Wenxiu, Huang, Xinghe, Huang, Xinsheng, Huang, Xinxin, Hui, Jiliang, Hui, Lijun, Hui, Zhongsheng, Huo, Fangjie, Ji, Runqing, Jia, Guojiong, Jia, Hao, Jia, Jingjing, Jia, Jingmei, Jia, Xiaoling, Jiang, Hua, Jiang, Jingcheng, Jiang, Qian, Jiang, Xianyan, Jiang, Xiaoyuan, Jiang, Yanxiang, Jiao, Yunhong, Jie, Liying, Jin, Binbin, Jin, Lingjiao, Jin, Renshu, Jin, Rong, Jin, Xiang, Jin, Xianping, Jin, Yongfan, Jin, Zepu, Jin, Zhenan, Jing, Chengrong, Jing, Jiajie, Jing, Ruiling, Kang, Liping, Kang, Yu, Kong, Jianqiong, Kou, Shijie, Kou, Xianli, Kulaxihan, Lai, Jijia, Lei, Lubi, Li, Baoxiang, Li, Bin, Li, Bing, Li, Chaohui, Li, Cheng, Li, Chunmei, Li, Chunyan, Li, Daqing, Li, Deen, Li, Di, Li, Feng, Li, Guanyi, Li, Haiyang, Li, Hongwei, Li, Jia, Li, Jialin, Li, Jianan, Li, Jianguang, Li, Jiaying, Li, Jing, Li, Jinmei, Li, Lala, Li, Li, Li, Lijun, Li, Liping, Li, Lize, Li, Mingju, Li, Minglan, Li, Mingyan, Li, Na, Li, Nan, Li, Nana, Li, Qiang, Li, Qianru, Li, Rui, Li, Ruihong, Li, Shanshan, Li, Shilin, Li, Si, Li, Suwen, Li, Tongshe, Li, Tongying, Li, Wanke, Li, Wei, Li, Wenbo, Li, Wenjuan, Li, Xi, Li, Xiangxia, Li, Xiao, Li, Xiaohui, Li, Xingyan, Li, Xiujuan, Li, Yan, Li, Yanfang, Li, Yang, Li, Yanxia, Li, Yaona, Li, Yichong, Li, Ying, Li, Yuqing, Li, Zheng, Li, Zhengye, Liang, Chuanliang, Liang, Jihua, Liang, Jin, Liang, Ke, Liang, Linju, Liang, Tingchen, Liang, Xia, Liang, Xianfeng, Liang, Yanli, Liang, Zhenye, Lie, Zhenbang, Lin, Qingfei, Lin, Ruifang, Lin, Xiao, Lin, Zhiqiang, Liu, Aijun, Liu, Chao, Liu, Chunxia, Liu, Cong, Liu, Fang, Liu, Guaiyan, Liu, Hongjun, Liu, Jiamin, Liu, Jiangling, Liu, Jianqi, Liu, Jieyun, Liu, Jihong, Liu, Jing, Liu, Jinsha, Liu, Juan, Liu, Junfang, Liu, Liming, Liu, Lin, Liu, Ling, Liu, Lu, Liu, Qiang, Liu, Qiaoling, Liu, Qiaoxia, Liu, Qiuxia, Liu, Shaobo, Liu, Xiaobao, Liu, Xiaocheng, Liu, Xiaoyuan, Liu, Xinbo, Liu, Xu, Liu, Yang, Liu, Yanhu, Liu, Yanming, Liu, Yaqin, Liu, Yong, Liu, Zhihong, Long, Jing, Lu, Futang, Lu, Huamei, Lu, Jiapeng, Lu, Junhong, Lu, Weibin, Lu, Yanrong, Lu, Yuchun, Luan, Tianwei, Luo, Qingwei, Luo, Qun, Luo, Tian, Luo, Xia, Luo, Yongmei, Lv, Jing, Lv, Jinhai, Lv, Lei, Lv, Lili, Lv, Meng, Ma, Aiqing, Ma, Huaimin, Ma, Huihuang, Ma, Jie, Ma, Jinbao, Ma, Li, Ma, Lingzhen, Ma, Nan, Ma, Qiaojuan, Ma, Shumei, Ma, Tengfei, Ma, Xiange, Ma, Xiaowen, Ma, Yuehua, Mai, Lanxian, Mei, Xiao, Meng, Gen, Miao, Ruichao, Miao, Xue, Miao, Xuyan, Min, Tingting, Mo, Shubing, Morigentu, Nan, Tingyan, Ni, Jinyang, Ni, Shuguo, Nie, Yu, Ning, Benxing, Ning, Xiaowei, Niu, Manman, Niu, Qingying, Niu, Wentang, Niu, Xiaoxia, Ou, Fang, Pan, Biyun, Pan, Chengjie, Pan, Congming, Pan, Jieli, Pan, Xiaowen, Pan, Ziying, Pei, Guangzhong, Pei, Lingyu, Pei, Min, Pei, Yanzhen, Peng, Yinyu, Peng, Yuming, Pu, Zhaokun, Qi, Fengjun, Qi, Liwei, Qi, Meiqiong, Qi, Yan, Qian, Jun, Qin, Lei, Qin, Zhonghua, Qing, Lan, Qiu, Lixia, Qiu, Weiyu, Qiu, Xiaoling, Qu, Yueli, Quan, Minghua, Ren, Dingping, Ren, Hong, Ren, Lingzhi, Ren, Tingting, Ren, Wei, Ren, Yihui, Rong, Yufang, Ruan, Jiahui, Shang, Peiqin, Shao, Minyan, Shao, Xuefeng, Shao, Yuling, Shen, Junrong, Shen, Rui, Sheng, Lin, Shi, Jiangjie, Shi, Xun, Shi, Yanhong, Shi, Yeju, Shi, Yujiao, Shu, Bo, Song, Bingchun, Song, Dan, Song, Jinhui, Song, Jinwang, Song, Jinxian, Song, Wei, Song, Xiaoping, Song, Yawen, Su, He, Su, Qinfeng, Su, Shuhong, Su, Xiaozhou, Sun, Chengxiang, Sun, Fangfang, Sun, Gongping, Sun, Jiangnan, Sun, Mengmeng, Sun, Rongrong, Sun, Shuting, Sun, Songtao, Sun, Ying, Sun, Yongmiao, Sun, Yunhong, Sun, Zhiqiang, Suo, Mengying, Tan, Binghu, Tang, Chunyan, Tang, Zhongli, Tao, Yu, Tian, Changming, Tian, Hongmei, Tian, Jian, Tian, Xiaomin, Wan, Huaibin, Wan, Qin, Wan, Rongjun, Wang, Bobin, Wang, Chao, Wang, Chaoqun, Wang, Chengliang, Wang, Di, Wang, Enfang, Wang, Feng, Wang, Gang, Wang, Guangqiang, Wang, Guixiang, Wang, Haifeng, Wang, Haijun, Wang, Haiyang, Wang, Jianfang, Wang, Jianfeng, Wang, Jing, Wang, Junping, Wang, Junying, Wang, Kang, Wang, Lei, Wang, Lin, Wang, Lize, Wang, Meng, Wang, Pan, Wang, Qi, Wang, Qiong, Wang, Qiuli, Wang, Qiuxue, Wang, Ran, Wang, Shaojin, Wang, Shuai, Wang, Tao, Wang, Tiantian, Wang, Tinghui, Wang, Tongyan, Wang, Wanhong, Wang, Wenjuan, Wang, Wenyan, Wang, Wenying, Wang, Wenzhuan, Wang, Xiaofei, Wang, Xiaoyan, Wang, Xitong, Wang, Xu, Wang, Yan, Wang, Yanfang, Wang, Yang, Wang, Yanping, Wang, Yanying, Wang, Yaoxin, Wang, Yingli, Wang, Yiting, Wang, Yue, Wang, Yumei, Wang, Yuzhuo, Wang, Zhenhua, Wang, Zhifang, Wang, Zhimin, Wei, Chunli, Wei, Lixia, Wei, Pei, Wei, Shuying, Wei, Xiqing, Wen, Hong, Wen, Yun, Wu, Chaoqun, Wu, Hairong, Wu, Lihua, Wu, Lingxiang, Wu, Qi, Wu, Shaorong, Wu, Wenting, Wu, Xueyi, Wu, Yongshuan, Wu, Zhihao, Wu, Zhuying, Wu, Zongyin, Wuhanbilige, Xia, Jun, Xia, Yang, Xiang, Jing, Xiao, Heliu, Xiao, Yaying, Xie, Meiling, Xie, Yinyan, Xin, Huiling, Xing, Jing, Xiu, Guoquan, Xu, Baohua, Xu, Chuangze, Xu, En, Xu, Jian, Xu, Shuli, Xu, Wei, Xu, Wen, Xue, Na, Xue, Tingting, Xue, Wei, Yan, Haiyan, Yan, Xiaofang, Yan, Yanqing, Yang, Bo, Yang, Hui, Yang, Huiyu, Yang, Jinhua, Yang, Kun, Yang, Man, Yang, Mengya, Yang, Ning, Yang, Ping, Yang, Xiajiao, Yang, Xiaomo, Yang, Xin, Yang, Xiujuan, Yang, Xuemei, Yang, Xuming, Yang, Yan, Yang, Yanhua, Yang, Yi, Yang, Yuanyuan, Yang, Zhimei, Yang, Zhiming, Yao, Hui, Yao, Lu, Ye, Jinling, Ye, Wenhua, Yi, Mingjiao, Yi, Shaowei, Yi, Wenyi, Yi, Zhimin, Yin, Guangxia, Yin, Guoyuan, Yu, Guibin, Yu, Hairong, Yu, Huaitao, Yu, Lijie, Yu, Lijun, Yu, Nana, Yu, Qin, Yu, Xinli, Yu, Yi, Yuan, Biao, Zeng, Chunmei, Zhai, Na, Zhai, Xiaojuan, Zhan, Hongju, Zhang, Aizhen, Zhang, Baohua, Zhang, Bin, Zhang, Caizhu, Zhang, Chaoying, Zhang, Chengbo, Zhang, Chunlai, Zhang, Churuo, Zhang, Fan, Zhang, Feiqin, Zhang, Ge, Zhang, Haibo, Zhang, Hailin, Zhang, Hanxue, Zhang, Huaixing, Zhang, Hui, Zhang, Huijuan, Zhang, Jinguo, Zhang, Jingyu, Zhang, Jinyun, Zhang, Jisheng, Zhang, Jun, Zhang, Lei, Zhang, Li, Zhang, Liang, Zhang, Lifeng, Zhang, Lina, Zhang, Liping, Zhang, Min, Zhang, Ping, Zhang, Qiang, Zhang, Rufang, Zhang, Ruifen, Zhang, Shengde, Zhang, Siqi, Zhang, Sufang, Zhang, Tingting, Zhang, Wanyue, Zhang, Weiliang, Zhang, Xiaohan, Zhang, Xiaohong, Zhang, Xiaojuan, Zhang, Xin, Zhang, Xue, Zhang, Xuewei, Zhang, Yachen, Zhang, Yang, Zhang, Yanyan, Zhang, Yaojie, Zhang, Yingyu, Zhang, Yuan, Zhang, Yun, Zhang, Yunfeng, Zhang, Zaozhang, Zhang, Zhichao, Zhao, Baihui, Zhao, Dan, Zhao, Fuxian, Zhao, Guizeng, Zhao, Haijie, Zhao, Honglei, Zhao, Huizhen, Zhao, Jindong, Zhao, Juan, Zhao, Liming, Zhao, Ling, Zhao, Lingshan, Zhao, Qingxia, Zhao, Qiuping, Zhao, Wanchen, Zhao, Wangxiu, Zhao, Weiyi, Zhao, Xiaodi, Zhao, Xiaojing, Zhao, Xiaoli, Zhao, Xiaoyan, Zhao, Xiling, Zhao, Yannan, Zhao, Yiyuan, Zheng, Shuzhen, Zheng, Xin, Zhi, Lixia, Zhong, Hui, Zhong, Qing, Zhong, Xin, Zhong, Yunzhi, Zhou, Jianfeng, Zhou, Jihu, Zhou, Ke, Zhou, Liangliang, Zhou, Ling, Zhou, Na, Zhou, Shengcheng, Zhou, Suyun, Zhou, Tao, Zhou, Wanren, Zhou, Weifeng, Zhou, Weijuan, Zhou, Xiaohong, Zhou, Yunke, Zhou, Yuquan, Zhou, Zhaohai, Zhou, Zhiming, Zhu, Bingpo, Zhu, Jifa, Zhu, Jing, Zhu, Mengnan, Zhu, Youcun, Zong, Dafei, Zuo, Hongbo, and Zuo, Zhaokai

Published
2024
Full Text
View/download PDF

27. Endovascular therapy in acute ischaemic stroke with large infarction with matched or mismatched clinical-radiological severities: a post-hoc analysis of the ANGEL-ASPECT trial

Author

Wang, Yongjun, Wang, Yilong, Liu, Liping, Liebeskind, David S., Miao, Zhongrong, Ren, Zeguang, Pereira, Vitor Mendes, Ji, Xunming, Dong, Qiang, Xu, Anding, Liu, Xinfeng, Yang, Qingwu, Jing (Chair), Jing, Zhang, Zhe, Zhang, Yingkui, Wu, Wei, Sun, Dapeng, Qi, Zhongqi, Li, Shuo, Liu, Zhenqiang, Yu, Zequan, Zhang, Jingyu, Chen, Fangguang, Li, Kangyue, Zhang, Kai, Hu, Mingkai, Liu (Chair), Jianmin, Yao, Chen, Chen, Kangning, Fang (Chair), Kun, Song, Bo, Dong, Yi, Huo, Xiaochuan, Ma, Gaoting, Yuan, Guangxiong, Han, Hongxing, Chen, Wenhuo, Wei, Ming, Zhang, Jiangang, Zhou, Zhiming, Yao, Xiaoxi, Wang, Guoqing, Song, Weigen, Cai, Xueli, Nan, Guangxian, Li, Di, Wang, Yizhou, Ling, Wentong, Cai, Chuwei, Wen, Changming, Wang, En, Zhang, Liyong, Jiang, Changchun, Liu, Yajie, Liao, Geng, Chen, Xiaohui, Li, Tianxiao, Liu, Shudong, Li, Jinglun, Sun, Yaxuan, Xu, Na, Gao, Zong’en, Ju, Dongsheng, Song, Cunfeng, Xuan, Jinggang, Zhou, Feng, Shi, Qing, Luo, Jun, Liu, Yan, Guo, Zaiyu, Li, Tong, Zheng, Hongbo, Dai, Linzhi, Zhao, Junfeng, Gui, Liqiang, Geng, Xiaokun, Tang, Yufeng, Yin, Congguo, Yang, Hua, An, Ruiyang, Sun, Yuying, Wu, Yanan, Yu, Chunlai, Zheng, Shuangcheng, Pan, Yuesong, Jin, Aoming, Xiang, Xianglong, Wang, Mengxing, Yan, Hongyi, He, Yuanling, Li, Chunyang, Kong, Weixia, Chen, Yuhuan, Guo, Chenhao, Ji, Fengjie, Ji, Pengshan, Liu, Lei, Lu, Xinghua, Luo, Guangkuo, Wang, Nanjing, Zhang, Yu, Liu, Bo, Yang, Jian, Deng, Jingjing, Wang, Juan, Wang, Wanru, Yu, Hang, Cui, Le, Liu, Wenwen, Wang, Ziyong, Zhao, Xia, Zhou, Zhou, Yi-Chou Wang, Alvin, Zheng, Lina, Nie, Ximing, Liu, Xin, Duan, Wanying, Liu, Jingyi, Wei, Yufei, Wen, Miao, Yang, Zhonghua, Leung, Thomas W., Nguyen, Thanh N., and Leng, Xinyi

Published
2024
Full Text
View/download PDF

29. Intravenous Tirofiban Versus Alteplase Before Endovascular Treatment in Acute Ischemic Stroke: A Pooled Analysis of the DEVT and RESCUE BT Trials

Author

Sang, Hongfei, Cao, Zhihua, Du, Jie, Nguyen, Thanh N., Saver, Jeffrey L., Mao, An, Nogueira, Raul G., Tao, Zhaojun, Zhou, Simin, Han, Qin, Sun, Dong, Lei, Bo, Liu, Shudong, Zeng, Guoyong, Yin, Congguo, Xie, Dongjing, Luo, Weidong, Jin, Zhenglong, Qiu, Zhongming, Yang, Qingwu, Wu, Deping, Shi, Zhonghua, Huang, Wenguo, Liu, Wenhua, Qiu, Tao, Zhou, Peiyang, Wang, Li, Fu, Xinmin, Yang, Shiquan, Zhang, Shuai, Zhou, Zhiming, Wang, Yan, Luo, Jun, Bai, Yongjie, Zhang, Min, Wu, Youlin, Wan, Yue, Wen, Changming, Wen, Hongbin, Ling, Wentong, Chen, Zhuo., Peng, Miao, Ai, Zhibing, Guo, Fuqiang, Guo, Jing, Guan, Haitao, Wang, Zhiyi, Liu, Yong, Pu, Jie, Wang, Zhen, Yang, Qingwu, Liu, Wenhua, Li, Huagang, Huang, Wenguo, Zhang, Min, Zhou, Peiyang, Zhou, Zhiming, Song, Bo, Wen, Changming, Yuan, Guangxiong, Luo, Jun, Zheng, Chong, Wang, Shouchun, Wang, Tao, Qi, Li, Wan, Yue, Wu, Youlin, Peng, Daizhou, Chang, Mingze, Shi, Zhonghua, Jin, Ying, Huang, Chuming, Liu, Tianzhu, Zhao, Wenlong, Wang, Jian, Wang, Li, Liu, Shugai, Luo, Shiwei, Pu, Jie, Chen, Shengli, Sun, Yaxuan, Jiang, Shunfu, Wei, Liping, Fu, Xinmin, Bai, Yongjie, Yang, Shunyu, Hu, Wei, Zhang, Guling, Pan, Chengde, Zhang, Shuai, Wang, Yan, Cao, Wenfeng, Yang, Shiquan, Zhang, Jun, Guo, Fuqiang, Wen, Hongbin, Zhang, Jinhua, and Lu, Mengjie

Published
2024
Full Text
View/download PDF

37. The Role of Hyperdense Basilar Artery Sign in Predicting Outcome of Acute Basilar Artery Occlusion within Twelve Hours of Onset

Author

Liu, Xinfeng, Wang, Guoping, Nogueira, Raul G., Qureshi, Adnan I., Baxter, Blaise W., Xu, Gelin, Yan, Xiaoyan, Gao, Feng, Jiao, Liqun, Qun, Sen, Wang, Zi, Chen, Juan, Ye, Ruidong, Zhang, Yongwei, Wu, Cangjun, Li, Rui, Fang, Chuanqing, Deng, Kexue, Yuan, Shuya, Zheng, Menglong, Chen, Hongbing, Zhang, Guang, Bao, Wei, Han, Hongxing, Yuan, Guangxiong, Wen, Changming, Zhou, Peiyang, Chen, Wenhuo, Zeng, Guoyong, Xu, Hui, Li, Yuwen, Ma, Zhengfei, Yu, Chuanqing, Su, Junfeng, Zhou, Zhiming, Chen, Zhongjun, Liao, Geng, Sun, Yaxuan, Ren, Youquan, Zhang, Hui, Chen, Jie, Yue, Xincan, Ma, Xiuyao, Xiao, GuoDong, Wang, Li, Liu, Rui, Yang, Weimin, Liu, Wenhua, Liu, Yong, Guo, Fuqiang, Cai, Xueli, Yin, Bo, Li, Jinglun, Fang, Pu, Shen, Chunyun, Ni, Chuyuan, Wang, Hui, Liu, Liang, Li, Kai, Cui, Tao, Wang, Hao, Gao, Jun, Yi, Tingyu, Wang, Youmeng, Wang, Tao, Shi, Xueying, Cao, Zhihua, Long, Chen, Chen, Li, Zhang, Chi, Zhai, Gichao, Zhang, Xia, Liang, Xiushan, Li, Qingsong, Meng, Yuhan, Tao, Jianbo, Zhu, Zhenzhu, Cheng, Yuedong, Zhang, Meng, Zhou, Tong, Wang, Jing, Zhang, Yali, Hu, Xiaohui, Tao, Chunrong, Yin, Yamei, Liu, Huanhuan, Tan, Xianhong, Hou, Siyang, Xie, Sanpin, Huo, Longwen, Zhu, Yuyou, Gong, Daokai, and Hu, Wei

Published
2024
Full Text
View/download PDF

40. Towards Generalized Implementation of Wasserstein Distance in GANs

Author

Xu, Minkai, Zhou, Zhiming, Lu, Guansong, Tang, Jian, Zhang, Weinan, and Yu, Yong

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models. However, in practice it does not always outperform other variants of GANs. This is mostly due to the imperfect implementation of the Lipschitz condition required by the KR duality. Extensive work has been done in the community with different implementations of the Lipschitz constraint, which, however, is still hard to satisfy the restriction perfectly in practice. In this paper, we argue that the strong Lipschitz constraint might be unnecessary for optimization. Instead, we take a step back and try to relax the Lipschitz constraint. Theoretically, we first demonstrate a more general dual form of the Wasserstein distance called the Sobolev duality, which relaxes the Lipschitz constraint but still maintains the favorable gradient property of the Wasserstein distance. Moreover, we show that the KR duality is actually a special case of the Sobolev duality. Based on the relaxed duality, we further propose a generalized WGAN training scheme named Sobolev Wasserstein GAN (SWGAN), and empirically demonstrate the improvement of SWGAN over existing methods with extensive experiments., Comment: Accepted by AAAI 2021

Published
2020

41. Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency

Author

Lu, Guansong, Zhou, Zhiming, Shen, Jian, Chen, Cheng, Zhang, Weinan, and Yu, Yong

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning. However, existing methods either not explicitly learn the transport map or do not support general cost function. In this paper, we propose an end-to-end approach for large-scale optimal transport, which directly solves the transport map and is compatible with general cost function. It models the transport map via stochastic neural networks and enforces the constraint on the marginal distributions via adversarial training. The proposed framework can be further extended towards learning Monge map or optimal bijection via adopting cycle-consistency constraint(s). We verify the effectiveness of the proposed method and demonstrate its superior performance against existing methods with large-scale real-world applications, including domain adaptation, image-to-image translation, and color transfer.

Published
2020

46. Application value of dual-source virtual non-contrast CT combined with AI in diagnosis of acute intracranial hemorrhage

Author

BAI Shanwei, WEI Xin, ZHOU Zhiming, AI Guangyong, ZHANG Rong, and CHEN Jinhua

Subjects
tomography, x-ray computed, virtual non-contrast, intracranial hemorrhage, artificial intelligence, Medicine (General), R5-920
Abstract

Objective To explore the clinical value of dual-source virtual non-contrast (VNC) CT combined with artificial intelligence (AI) in the diagnosis of acute intracranial hemorrhage. Methods A cross-sectional study was conducted on the imaging data of non-contrast CT and dual-energy CT angiography (CTA) in 67 patients with suspected intracranial hemorrhage. They were 32 males and 35 females, at an average age of 56.2±12.5 (35~89) years. The differences of average CT value, noise, signal to noise ratio (SNR), contrast noise ratio (CNR) and radiation dose between VNCT and NCCT were analyzed. Taken the common diagnosis results of two radiologists as the reference standard, the type of intracranial hemorrhage, the degree of midline structural deviation, the long and short diameters of the largest hemorrhage layer and the volume of hematoma were analyzed by AI software under VNCT and NCCT images. And the time taken by radiologists and AI to obtain the above quantitative evaluation indexes was compared. Results In the objective evaluation, the average CT value, SNR and CNR were significantly lower (P < 0.001), and the noise was higher in the VNCT images than the NCCT images (P < 0.001). The radiation dose of VNCT was lower by 75.6% than that of NCCT+CTA (P < 0.001). The qualitative analysis indicated that the accuracy of AI in diagnosing intracranial hemorrhage on NCCT and VNCT images was 94.0% and 89.6% respectively. The accuracy rates of VNCT+AI for IPH, IVH, SAH and SDH were 83.6%, 86.0%, 83.0% and 60.0%, respectively, which had no differences when compared with those of NCCT+AI (all P>0.05). In the quantitative analysis, VNCT+AI had good consistency with manual measurement results in terms of the above indicators (ICC=0.820, 0.942, 0.920, and 0.959, P < 0.001). In terms of the time required for AI diagnosis, VNCT need significantly shorter time than NCCT(50.6±15.9 vs 58.5±24.9 s, P < 0.001). Conclusion Dual-source VNC technology has low radiation dose, simple and fast examination process, and high accuracy in the diagnosis of acute intracranial hemorrhage when combined with AI. And the quantitative evaluation indexes of VNCT+AI are in good consistency with radiologists and has potential clinical application value.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results