检索结果-内蒙古大学图书馆

SI-LSGAN: Complex network structure inference based on least square generative adversarial network

CHAOS SOLITONS & FRACTALS 2023年第1期173卷

作者： Liu, Jie Deng, Wenfeng Yang, Chunhua Qin, Aina Huang, Keke Cent South Univ Sch Automat Changsha 410083 Hunan Peoples R China

The problem of inferring the underlying structure from available data is important to understanding and controlling the dynamic behavior of complex systems. Although many efforts have been put forward to address this problem, their performance remains limited due to the lack of effective application of structure prior knowledge. Inspired by the powerful feature extraction capabilities of deep learning, this paper develops a complex network structure inference method based on least square generative adversarial network (SI-LSGAN) to promote the network structure inference performance. Specifically, we first construct the problem of network structure inference in the least squares paradigm. Then, a generator neural network is trained to fit the nonlinear mapping relationship between the measurement data and network structure. Next, a discriminator neural network is trained to distinguish the generated samples by incorporating the characteristics of degree distribution and binarization of network structure. Following the adversarial training principle, the generator and discriminator promote each other, and the inference result that conforms to the prior knowledge of the target network can be obtained from the observable data. Experimental results have demonstrated the effectiveness in the fusion of structure prior knowledge, which improves the inference accuracy and efficiency.

关键词： Complex network network structure inference Least square generative adversarial network Prior knowledge

来源：评论

学校读者我要写书评

暂无评论

structure inference of networked system with the synergy of deep residual network and fully connected layer network

引用

NEURAL networkS 2022年第0期145卷 288-299页

作者： Huang, Keke Li, Shuo Deng, Wenfeng Yu, Zhaofei Ma, Lei Cent South Univ Sch Automat Changsha 410083 Peoples R China Peking Univ Inst Artificial Intelligence Beijing 100871 Peoples R China Peking Univ Dept Comp Sci & Technol Beijing 100871 Peoples R China Beijing Acad Artificial Intelligence Beijing 100085 Peoples R China

The networked systems are booming in multi-disciplines, including the industrial engineering system, the social system, and so on. The network structure is a prerequisite for the understanding and exploration of networked systems. However, the network structure is always unknown in practice, thus, it is significant yet challenging to investigate the inference of network structure. Although some model-based methods and data-driven methods, such as the phase-space based method and the compressive sensing based method, have investigated the structure inference tasks, they were time-consuming due to the greedy iterative optimization procedure, which makes them difficult to satisfy real-time structure inference requirements. Although the reconstruction time of L1 and other methods is short, the reconstruction accuracy is very low. Inspired by the powerful representation ability and time efficiency for the structure inference with the deep learning framework, a novel synergy method combines the deep residual network and fully connected layer network to solve the network structure inference task efficiently and accurately. This method perfectly solves the problems of long reconstruction time and low accuracy of traditional methods. Moreover, the proposed method can also fulfill the inference task of large scale complex network, which further indicates the scalability of the proposed method. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Complex network network structure inference Deep learning Residual network Compressive sensing

来源：评论

学校读者我要写书评

暂无评论

Scalable Probabilistic Model Selection for network Representation Learning in Biological network inference

Scalable Probabilistic Model Selection for Network Represent...

引用

作者： C., Kishan K. Rochester Institute of Technology

学位级别：Ph.D.

A biological system is a complex network of heterogeneous molecular entities and their interactions contributing to various biological characteristics of the system. Although the biological networks not only provide an elegant theoretical framework but also offer a mathematical foundation to analyze, understand, and learn from complex biological systems, the reconstruction of biological networks is an important and unsolved problem. Current biological networks are noisy, sparse and incomplete, limiting the ability to create a holistic view of the biological reconstructions and thus fail to provide a system-level understanding of the biological phenomena. Experimental identification of missing interactions is both time-consuming and expensive. Recent advancements in high-throughput data generation and significant improvement in computational power have led to novel computational methods to predict missing interactions. However, these methods still suffer from several unresolved challenges. It is challenging to extract information about interactions and incorporate that information into the computational model. Furthermore, the biological data are not only heterogeneous but also high-dimensional and sparse presenting the difficulty of modeling from indirect measurements. The heterogeneous nature and sparsity of biological data pose significant challenges to the design of deep neural network structures which use essentially either empirical or heuristic model selection methods. These unscalable methods heavily rely on expertise and experimentation, which is a time-consuming and error-prone process and are prone to overfitting. Furthermore, the complex deep networks tend to be poorly calibrated with high confidence on incorrect predictions. In this dissertation, we describe novel algorithms that address these challenges. In Part I, we design novel neural network structures to learn representation for biological entities and further expand the model to integrate heteroge

关键词： Beta-Bernoulli process Deep learning Link prediction network representation Learning network structure inference Probabilistic model selection

来源：评论

学校读者我要写书评

暂无评论

Modeling Gene Regulatory network Based on Non-homogeneous Dynamic Bayesian network 11

Modeling Gene Regulatory Network Based on Non-homogeneous Dy...

引用

11th International Conference on Bioinformatics and Computational Biology (ICBCB)

作者： Hu Chunling Zhang Qianqian Zhang Jiayao Hefei Uni Coll Artificial Intelligence & Big Data Hefei Peoples R China

ISBN: (纸本)9798350397871

Among methods for reconstructing gene regulatory networks, non-homogeneous dynamic Bayesian networks have received much attention because of their advantages of expressing both the regulatory relationships among genes and the strengths of relationships among genes. However, such models sample the parent node set randomly, and the selection of the candidate parent node set does not take into account the correlation between nodes, resulting in a low convergence speed of network reconstruction. This paper has proposed a non-homogeneous dynamic Bayesian network model based on parent node filtering (PF-NH-DBN). Firstly, PF-NH-DBN uses mutual information and time-series conditional mutual information to screen the initial set of candidate parent nodes. Thereby reducing the search space and further removing redundant edges, making network reconstruction more accurate. Secondly, the mutual information based on the Gaussian mutation strategy is proposed to avoid falling into the local optimum. Finally, the experimental results on synthetic and on real biological network data show that the new model yields better network reconstruction accuracies than the original model.

关键词： gene regulatory network non-homogeneous dynamic Bayesian network mutual information network structure inference

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：