检索结果-内蒙古大学图书馆

Identifying disease-related microbes based on multi-scale variational graph autoencoder embedding Wasserstein distance

引用

BMC BIOLOGY 2023年第1期21卷 294-294页

作者： Zhu, Huan Hao, Hongxia Yu, Liang Xidian Univ Sch Comp Sci & Technol Xian Peoples R China

BackgroundEnormous clinical and biomedical researches have demonstrated that microbes are crucial to human health. Identifying associations between microbes and diseases can not only reveal potential disease mechanisms, but also facilitate early diagnosis and promote precision medicine. Due to the data perturbation and unsatisfactory latent representation, there is a significant room for *** this work, we proposed a novel framework, Multi-scale variational graph autoencoder embedding Wasserstein distance (MVGAEW) to predict disease-related microbes, which had the ability to resist data perturbation and effectively generate latent representations for both microbes and diseases from the perspective of distribution. First, we calculated multiple similarities and integrated them through similarity network confusion. Subsequently, we obtained node latent representations by improved variational graph autoencoder. Ultimately, XGBoost classifier was employed to predict potential disease-related microbes. We also introduced multi-order node embedding reconstruction to enhance the representation capacity. We also performed ablation studies to evaluate the contribution of each section of our model. Moreover, we conducted experiments on common drugs and case studies, including Alzheimer's disease, Crohn's disease, and colorectal neoplasms, to validate the effectiveness of our ***, our model exceeded other currently state-of-the-art methods, exhibiting a great improvement on the HMDAD database.

关键词： variational graph autoencoder Wasserstein distance Microbe-disease association XGBoost

来源：评论

学校读者我要写书评

暂无评论

Epitomic variational graph autoencoder 25

Epitomic Variational Graph Autoencoder

引用

25th International Conference on Pattern Recognition (ICPR)

作者： Khan, Rayyan Ahmad Anwaar, Muhammad Umer Kleinsteuber, Martin Tech Univ Munich Munich Germany Mercateo AG Munich Germany

ISBN: (纸本)9781728188089

variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. [3] in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant number of latent variables fail to capture any information about the input data and the corresponding hidden units become inactive. This adversely affects learning diverse and interpretable latent representations. As variational graph autoencoder (VGAE) extends VAE for graph-structured data, it inherits the over-pruning problem. In this paper, we adopt a model based approach and propose epitomic VGAE (EVGAE), a generative variational framework for graph datasets which successfully mitigates the over-pruning problem and also boosts the generative ability of VGAE. We consider EVGAE to consist of multiple sparse VGAE models, called epitomes, that are groups of latent variables sharing the latent space. This approach aids in increasing active units as epitomes compete to learn better representation of the graph data. We verify our claims via experiments on three benchmark datasets. Our experiments show that EVGAE has a better generative ability than VGAE. Moreover, EVGAE outperforms VGAE on link prediction task in citation networks.

关键词： graph autoencoder variational graph autoencoder graph neural networks Over-pruning VAE EVGAE

来源：评论

学校读者我要写书评

暂无评论

Interpretable variational graph autoencoder with Noninformative Prior

引用

FUTURE INTERNET 2021年第2期13卷 51-51页

作者： Sun, Lili Liu, Xueyan Zhao, Min Yang, Bo Jilin Univ Coll Software Changchun 130012 Peoples R China Jilin Univ Minist Educ Key Lab Symbol Computat & Knowledge Engineer Changchun 130012 Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

variational graph autoencoder, which can encode structural information and attribute information in the graph into low-dimensional representations, has become a powerful method for studying graph-structured data. However, most existing methods based on variational (graph) autoencoder assume that the prior of latent variables obeys the standard normal distribution which encourages all nodes to gather around 0. That leads to the inability to fully utilize the latent space. Therefore, it becomes a challenge on how to choose a suitable prior without incorporating additional expert knowledge. Given this, we propose a novel noninformative prior-based interpretable variational graph autoencoder (NPIVGAE). Specifically, we exploit the noninformative prior as the prior distribution of latent variables. This prior enables the posterior distribution parameters to be almost learned from the sample data. Furthermore, we regard each dimension of a latent variable as the probability that the node belongs to each block, thereby improving the interpretability of the model. The correlation within and between blocks is described by a block-block correlation matrix. We compare our model with state-of-the-art methods on three real datasets, verifying its effectiveness and superiority.

关键词： neural networks network representation learning noninformative prior distribution variational graph autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attention-Based variational graph autoencoder

引用

IEEE ACCESS 2020年 8卷 152637-152645页

作者： Weng, Ziqiang Zhang, Weiyu Dou, Wei Shandong Acad Sci Qilu Univ Technol Sch Comp Sci & Technol Jinan 250353 Peoples R China

autoencoders have been successfully used for graph embedding, and many variants have been proven to effectively express graph data and conduct graph analysis in low-dimensional space. However, previous methods ignore the structure and properties of the reconstructed graph, or they do not consider the potential data distribution in the graph, which typically leads to unsatisfactory graph embedding performance. In this paper, we propose the adversarial attention variational graph autoencoder (AAVGA), which is a novel framework that incorporates attention networks into the encoder part and uses an adversarial mechanism in embedded training. The encoder involves node neighbors in the representation of nodes by stacking attention layers, which can further improve the graph embedding performance of the encoder. At the same time, due to the adversarial mechanism, the distribution of the potential features that are generated by the encoder are closer to the actual distribution of the original graph data;thus, the decoder generates a graph that is closer to the original graph. Experimental results prove that AAVGA performs competitively with state-of-the-art popular graph encoders on three citation datasets.

关键词： Attention layers adversarial mechanism variational graph autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep graph embedding learning based on multi-variational graph autoencoders for POI recommendation

引用

DATA MINING AND KNOWLEDGE DISCOVERY 2025年第4期39卷 1-21页

作者： Gong, Weihua Shen, Genhang Zhao, Anlun Yang, Lianghuai Cheng, Zhen Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Zhejiang Univ Sch Software Technol Ningbo 315048 Peoples R China

Recently, point-of-interest (POI) recommendation has become a popular research hotspot in heterogeneous location-based social network (LBSN). One major recurring challenge in POI recommendation is that most existing works fail to learn well graph embeddings for user preferences, lacking the capability of fusing multi-typed nodes and their interaction relations, e.g., users' check-in relations to POIs, following relations to online topics, and the social relations. To address this challenge, we propose a new unified heterogeneous graph embedding framework by leveraging multimodal variational graph autoencoders, called MultiVGAE. Specifically, we first employ multiple GCN-based encoders to learn the modality-specific latent embeddings for different entities in heterogeneous subgraphs of LBSN, with consideration of fusing multi-types of relations and multi-modal node features. And then reconstruct the corresponding subgraph structures through multiple decoders from the learned embeddings. Finally, extensive experiments have been conducted on two real-world datasets (e.g., Foursquare-NYC and Yelp2018), and the experimental results demonstrate that our proposed MultiVGAE achieves superior performance compared to the existing state-of-the-art baselines on POI recommendation.

关键词： Heterogeneous graph embedding variational graph autoencoder POI recommendation

来源：评论

学校读者我要写书评

暂无评论

Link Activation Using variational graph autoencoders

引用

IEEE COMMUNICATIONS LETTERS 2021年第7期25卷 2358-2361页

作者： Jamshidiha, Saeed Pourahmadi, Vahid Mohammadi, Abbas Bennis, Mehdi Amirkabir Univ Technol Dept Elect Engn Tehran 15914 Iran Univ Oulu Ctr Wireless Commun Oulu 90570 Finland

An unsupervised method is proposed for link activation in wireless networks by identifying clusters of interfering users. A k-nearest neighbors interference graph is first defined for the wireless network which is then mapped to a stochastic latent space. The users are then clustered in the latent space using a Gaussian mixture model, and one user from each interfering cluster is activated while the rest of the users in that cluster remain idle. The proposed framework is scalable, works across several network topologies such as device to device (D2D), and is close to the optimal solution in performance.

关键词： Interference Wireless networks Transmitters Device-to-device communication Stochastic processes Receivers Deep learning graph embedding variational graph autoencoder wireless networks Bayesian deep learning

来源：评论

学校读者我要写书评

暂无评论

Attention-guided variational graph autoencoders reveal heterogeneity in spatial transcriptomics

引用

BRIEFINGS IN BIOINFORMATICS 2024年第3期25卷 bbae173-bbae173页

作者： Lei, Lixin Han, Kaitai Wang, Zijun Shi, Chaojing Wang, Zhenghui Dai, Ruoyan Zhang, Zhiwei Wang, Mengqiu Guo, Qianjin Beijing Inst Petrochem Technol Acad Artificial Intelligence 19 Qingyuan North Rd Beijing 102617 Peoples R China

The latest breakthroughs in spatially resolved transcriptomics technology offer comprehensive opportunities to delve into gene expression patterns within the tissue microenvironment. However, the precise identification of spatial domains within tissues remains challenging. In this study, we introduce AttentionVGAE (AVGN), which integrates slice images, spatial information and raw gene expression while calibrating low-quality gene expression. By combining the variational graph autoencoder with multi-head attention blocks (MHA blocks), AVGN captures spatial relationships in tissue gene expression, adaptively focusing on key features and alleviating the need for prior knowledge of cluster numbers, thereby achieving superior clustering performance. Particularly, AVGN attempts to balance the model's attention focus on local and global structures by utilizing MHA blocks, an aspect that current graph neural networks have not extensively addressed. Benchmark testing demonstrates its significant efficacy in elucidating tissue anatomy and interpreting tumor heterogeneity, indicating its potential in advancing spatial transcriptomics research and understanding complex biological phenomena.

关键词： spatially resolved transcriptomics spatial clustering graph deep learning variational graph autoencoder attention-guided

来源：评论

学校读者我要写书评

暂无评论

HPOseq: a deep ensemble model for predicting the protein-phenotype relationships based on protein sequences

引用

BMC BIOINFORMATICS 2025年第1期26卷 1-15页

作者： Zhao, Kai Ji, Zhuocheng Zhang, Linlin Quan, Na Li, Yuheng Yu, Guanglei Bi, Xuehua Xinjiang Univ Sch Comp Sci & Technol Urumqi 830011 Peoples R China Xinjiang Univ Sch Software Urumqi 830011 Peoples R China Xinjiang Med Univ Coll Med Engn & Technol Urumqi 830011 Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China

BackgroundUnderstanding the relationships between proteins and specific disease phenotypes contributes to the early detection of diseases and advances the development of personalized medicine. The acquisition of a large amount of proteomics data has facilitated this process. To improve discovery efficiency and reduce the time and financial costs associated with biological experiments, various computational methods have yielded promising results. However, the lack of rich and reliable protein-related information still presents challenges in this *** this paper, we propose an ensemble prediction model, named HPOseq, which predicts human protein-phenotype relationships based only on sequence information. HPOseq establishes two base models to achieve objectives. One directly extracts internal information from amino acid sequences as protein features to predict the associated phenotypes. The other builds a protein-protein network based on sequence similarity, extracting information between proteins for phenotype prediction. Ultimately, an ensemble module is employed to integrate the predictions from both base models, resulting in the final *** results of 5-fold cross-validation reveal that HPOseq outperforms seven baseline methods for predicting protein-phenotype relationships. Moreover, we conduct case studies from the points of phenotype annotation and protein analysis to verify the practical significance of HPOseq.

关键词： Ensemble model variational graph autoencoder Deep learning Amino acid sequence

来源：评论

学校读者我要写书评

暂无评论

Designing Connectivity-Guaranteed Porous Metamaterial Units Using Generative graph Neural Networks

引用

JOURNAL OF MECHANICAL DESIGN 2025年第2期147卷 021706页

作者： Wang, Zihan Bray, Austin Khanghah, Kiarash Naghavi Xu, Hongyi Univ Connecticut Sch Mech Aerosp & Mfg Engn Storrs CT 06269 USA

Designing 3D porous metamaterial units while ensuring complete connectivity of both solid and pore phases presents a significant challenge. This complete connectivity is crucial for manufacturability and structure-fluid interaction applications (e.g., fluid-filled lattices). In this study, we propose a generative graph neural network-based framework for designing the porous metamaterial units with the constraint of complete connectivity. First, we propose a graph-based metamaterial unit generation approach to generate porous metamaterial samples with complete connectivity in both solid and pore phases. Second, we establish and evaluate three distinct variational graph autoencoder (VGAE)-based generative models to assess their effectiveness in generating an accurate latent space representation of metamaterial structures. By choosing the model with the highest reconstruction accuracy, the property-driven design search is conducted to obtain novel metamaterial unit designs with the targeted properties. A case study on designing liquid-filled metamaterials for thermal conductivity properties is carried out. The effectiveness of the proposed graph neural network-based design framework is evaluated by comparing the performances of the obtained designs with those of known designs in the metamaterial database. Merits and shortcomings of the proposed framework are also discussed.

关键词： porous metamaterial graph neural network variational graph autoencoder design optimization generative design connectivity data-driven design design of engineered materials system machine learning

来源：评论

学校读者我要写书评

暂无评论

Cross-domain recommendation via knowledge distillation

引用

KNOWLEDGE-BASED SYSTEMS 2025年 311卷

作者： Li, Xiuze Huang, Zhenhua Wu, Zhengyang Wang, Changdong Chen, Yunwen South China Normal Univ Sch Artificial Intelligence Foshan 528225 Guangdong Peoples R China South China Normal Univ Sch Comp Sci Guangzhou 510631 Guangdong Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China DataGrandInc Res & Dev Dept Shanghai 201203 Peoples R China

Recommendation systems frequently suffer from data sparsity, resulting in less-than-ideal recommendations. A prominent solution to this problem is Cross-Domain Recommendation (CDR), which employs data from various domains to mitigate data sparsity and cold-start issues. Nevertheless, current mainstream methods, like feature mapping and co-training exploring domain relationships, overlook latent user-user and user-item similarities in the shared user-item interaction graph. Spurred by these deficiencies, this paper introduces KDCDR, a novel cross-domain recommendation framework that relies on knowledge distillation to utilize the data from the graph. KDCDR aims to improve the recommendation performance in both domains by efficiently utilizing information from the shared interaction graph. Furthermore, we enhance the effectiveness of user and item representations by exploring the relationships between user-user similarity and item-item similarity, as well as user-item interactions. The developed scheme utilizes the inner-domain graph as a teacher and the cross-domain graph as a student, where the student learns by distilling knowledge from the two teachers after undergoing a high-temperature distillation process. Furthermore, we introduce dynamic weight that regulates the learning process to prevent the student network from overly favoring learning from one domain and focusing on learning knowledge that the teachers have taught incorrectly. Through extensive experiments on four real-world datasets, KDCDR demonstrates significant improvements over state-of-the-art methods, proving the effectiveness of KDCDR in addressing data sparsity issues and enhancing cross-domain recommendation performance. Our code and data are available at https://***/pandas-bondage/KDCDR.

关键词： Cross-domain recommendation Knowledge distillation variational graph autoencoder

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

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

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：