2篇
您的检索式：作者名="Jiadi Xing"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | microRNAs and ceRNAs: RNA networks in pathogenesis of cancer显示文摘microRNAs (miRNAs) are a class of endogenous, single-stranded non-coding RNAs of 2023 nucleotides in length, functioning as negative regulators of gene expression at the post-transcriptional level. The dysregulation of miRNAs has been demonstrated to play critical roles in tumorigenesis, either through inhibiting tumor suppressor genes or activating oncogenes inappropriately. Besides their promising clinical applications in cancer diagnosis and treatment, recent studies have uncovered that miRNAs could act as a regulatory language, through which messenger RNAs, transcribed pseudogenes, and long noncoding RNAs crosstalk with each other and form a novel regulatory network. RNA transcripts involved in this network have been termed as competing endogenous RNAs (ceRNAs), since they influence each other's level by competing for the same pool of miRNAs through miRNA response elements (MREs) on their target transcripts. The discovery of miRNA-ceRNA network not only provides the possibility of an additional level of post-transcriptional regulation, but also dictates a reassessment of the existing regulatory pathways involved in cancer initiation and progression. | Xiangqian Su Jiadi Xing Zaozao Wang Lei Chen Ming Cui Beihai Jiang | 2013 | Chinese Journal of Cancer Research2013，25，2： | 13 |
| 2 | ASCFL:Accurate and Speedy Semi-Supervised Clustering Federated Learning显示文摘The influence of non-Independent Identically Distribution(non-IID)data on Federated Learning(FL)has been a serious concern.Clustered Federated Learning(CFL)is an emerging approach for reducing the impact of non-IID data,which employs the client similarity calculated by relevant metrics for clustering.Unfortunately,the existing CFL methods only pursue a single accuracy improvement,but ignore the convergence rate.Additionlly,the designed client selection strategy will affect the clustering results.Finally,traditional semi-supervised learning changes the distribution of data on clients,resulting in higher local costs and undesirable performance.In this paper,we propose a novel CFL method named ASCFL,which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data.To deal with unlabeled data,the prediction labels strategy predicts labels by encoders.The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round.What is more,the similarity-based clustering strategy uses a new indicator to measure the similarity between clients.Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets. | Jingyi He Biyao Gong Jiadi Yang Hai Wang Pengfei Xu Tianzhang Xing | 2023 | Tsinghua Science and Technology2023，28，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员