Filters








10,956 Hits in 5.2 sec

Variational Approach for Learning Community Structures

Jun Jin Choong, Xin Liu, Tsuyoshi Murata
2018 Complexity  
Discovering and modeling community structure exist to be a fundamentally challenging task.  ...  In domains such as biology, chemistry, and physics, researchers often rely on community detection algorithms to uncover community structures from complex systems yet no unified definition of community  ...  Variational Graph Autoencoder (VGAE) [15] extends the problem of learning network embedding to a generative perspective by leveraging on the Variational Autoencoder (VAE) framework [45] .  ... 
doi:10.1155/2018/4867304 fatcat:5eten4ttw5e7bdnubmngrcnzkm

Dynamic Joint Variational Graph Autoencoders [article]

Sedigheh Mahdavi, Shima Khoshraftar, Aijun An
2019 arXiv   pre-print
Each auto-encoder embeds a graph snapshot based on its local structure and can also learn temporal dependencies by collaborating with other autoencoders.  ...  In this paper, we propose Dynamic joint Variational Graph Autoencoders (Dyn-VGAE) that can learn both local structures and temporal evolutionary patterns in a dynamic network.  ...  We first assign a specific variational autoencoder with a modified learning function for each graph snapshot.  ... 
arXiv:1910.01963v1 fatcat:myz7j7fi6zgzzmuwue55sof34q

Network Embedding via Community Based Variational Autoencoder

Wei Shi, Ling Huang, Chang-Dong Wang, Juan-Hui Li, Yong Tang, Chengzhou Fu
2019 IEEE Access  
INDEX TERMS Network embedding, community detection, variational autoencoder.  ...  In this paper, we propose a communitybased variational autoencoder (ComVAE) model to learn network embedding, which consists of a community detection module and a deep learning module.  ...  DEEP LEARNING MODULE In this section, we introduce in detail the architecture of deep learning module in ComVAE and explain how the conditional variational autoencoder can integrate local information with  ... 
doi:10.1109/access.2019.2900662 fatcat:vhsz7puq5vc7rb2xkbe4vei7gm

Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design

Eugene Lin, Chieh-Hsin Lin, Hsien-Yuan Lane
2020 Molecules  
A growing body of evidence now suggests that artificial intelligence and machine learning techniques can serve as an indispensable foundation for the process of drug design and discovery.  ...  In light of latest advancements in computing technologies, deep learning algorithms are being created during the development of clinically useful drugs for treatment of a number of diseases.  ...  [27] incorporated the variational autoencoder structure with the deep adversarial autoencoder structure to create the deep adversarial variational autoencoder structure, which is described in Section  ... 
doi:10.3390/molecules25143250 pmid:32708785 fatcat:rrik322g6vbetaubwjb3rtvajm

A Comprehensive Survey on Community Detection with Deep Learning [article]

Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu
2021 arXiv   pre-print
Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages  ...  Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to academics and practitioners.  ...  for VGAECD Community Detection [125] Learning community structure with variational autoencoder Optimizing Variational Graph Autoencoder VGAECD-OPT for Community Detection [136] Optimizing variational  ... 
arXiv:2105.12584v2 fatcat:matipshxnzcdloygrcrwx2sxr4

Deep learning identifies partially overlapping subnetworks in the human social brain

Hannah Kiesow, R. Nathan Spreng, Avram J. Holmes, M. Mallar Chakravarty, Andre F. Marquand, B. T. Thomas Yeo, Danilo Bzdok
2021 Communications Biology  
We explored coherent representations of structural co-variation at population scale within a recent social brain atlas, by translating autoencoder neural networks from deep learning.  ...  The learned subnetworks revealed essential patterns of structural relationships between social brain regions, with the nucleus accumbens, medial prefrontal cortex, and temporoparietal junction embedded  ...  In this way, hidden subnetwork representations were directly learned from the brain-imaging data themselves by translating autoencoder network solutions from the deep learning community.  ... 
doi:10.1038/s42003-020-01559-z pmid:33446815 fatcat:vzt2vkc4fbfe5ec7h46774ayte

Optimizing Variational Graph Autoencoder for Community Detection with Dual Optimization

Jun Jin Choong Xin Liu, Tsuyoshi Murata
2020 Entropy  
Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially  ...  Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs.  ...  network with community structure.  ... 
doi:10.3390/e22020197 pmid:33285972 pmcid:PMC7516625 fatcat:i4u2ffdpdffy3cxoa4fow2wnwu

Joint Transceiver Optimization for Wireless Communication PHY with Convolutional Neural Network [article]

Banghua Zhu, Jintao Wang, Longzhuang He, Jian Song
2018 arXiv   pre-print
Furthermore, the proposed system network is more robust to channel variation than traditional communication methods.  ...  In this paper, we propose a novel neural network structure for jointly optimizing the transmitter and receiver in communication physical layer under fading channels.  ...  In deep learning based communication systems, it is possible to optimize the transmitter and receiver jointly with a structure of autoencoder [19] instead of artificially introduced block schemes [20  ... 
arXiv:1808.03242v1 fatcat:m5quxocxfnhh5emu4d4uj47bii

Interpretable Variational Graph Autoencoder with Noninformative Prior

Lili Sun, Xueyan Liu, Min Zhao, Bo Yang
2021 Future Internet  
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  ...  Given this, we propose a novel noninformative prior-based interpretable variational graph autoencoder (NPIVGAE).  ...  [22] expanded [23] and proposed a variational graph autoencoder based on the community discovery task.  ... 
doi:10.3390/fi13020051 fatcat:zrrhkfz25bbdrhuscc5zq62qk4

Deep Learning in Resource and Data Constrained Edge Computing Systems [chapter]

Pranav Sharma, Marcus Rüb, Daniel Gaida, Heiko Lutz, Axel Sikora
2020 Technologien für die intelligente Automation  
In this paper, we perform unsupervised deep learning utilizing variational autoencoders and demonstrate that federated learning is a communication efficient concept for machine learning that protects data  ...  As an example, variational autoencoders are utilized to cluster and visualize data from a microelectromechanical systems foundry.  ...  Variational Autoencoder Autoencoders belong to the family of unsupervised machine learning methods and are used for dimensionality reduction.  ... 
doi:10.1007/978-3-662-62746-4_5 fatcat:tjclm5bav5hdpjycpskxp3veoi

Robustness of autoencoders for establishing psychometric properties based on small sample sizes: results from a Monte Carlo simulation study and a sports fan curiosity study

Yen-Kuang Lin, Chen-Yin Lee, Chen-Yueh Chen
2022 PeerJ Computer Science  
The feasibility of autoencoders with small sample sizes was examined.  ...  Methodology A Monte Carlo simulation was conducted, varying the levels of non-normality, sample sizes, and levels of communality.  ...  Tie-weighted autoencoder An autoencoder is a neural network with a symmetrical structure.  ... 
doi:10.7717/peerj-cs.782 pmid:35494838 pmcid:PMC9044230 fatcat:iq2jadkhkzgcpg62uy2hxqhleu

Low Complexity Autoencoder based End-to-End Learning of Coded Communications Systems [article]

Nuwanthika Rajapaksha, Nandana Rajatheva, Matti Latva-aho
2020 arXiv   pre-print
End-to-end learning of a communications system using the deep learning-based autoencoder concept has drawn interest in recent research due to its simplicity, flexibility and its potential of adapting to  ...  In this paper, we have compared the bit error rate (BER) performance of autoencoder based systems and conventional channel coded systems with convolutional coding (CC), in order to understand the potential  ...  For that, we have implemented a model similar to the original autoencoder pro-posed by [3] with slight variations.  ... 
arXiv:1911.08009v2 fatcat:qq3lxh26afeufk2yxuxgy5uae4

Deep Learning for the Degraded Broadcast Channel [article]

Erik Stauffer, Andy Wang, Nihar Jindal
2019 arXiv   pre-print
Machine learning has shown promising results for communications system problems.  ...  We present results on the use of deep auto-encoders in order to learn a transceiver for the multiuser degraded broadcast channel, and see that the auto encoder is able to learn to communicate on this channel  ...  Multiuser Autoencoder Configuration: Following the autoencoder architecture for communication over AWGN from [1] , we construct the following autoencoder structure for the degraded broadcast channel.  ... 
arXiv:1903.08577v1 fatcat:mtll463iovhangiw23jpkjvy5i

Learning Graph Embedding with Adversarial Training Methods [article]

Shirui Pan, Ruiqi Hu, Sai-fu Fung, Guodong Long, Jing Jiang, Chengqi Zhang
2019 arXiv   pre-print
Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder  ...  (ARVGA), to learn the graph embedding effectively.  ...  In this paper, we propose a novel adversarially regularized algorithm with two variants, adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational  ... 
arXiv:1901.01250v2 fatcat:mgx6qkjxubf2rghtz6ffz4gite

Graph Representation Learning via Ladder Gamma Variational Autoencoders

Arindam Sarkar, Nikhil Mehta, Piyush Rai
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present a probabilistic framework for community discovery and link prediction for graph-structured data, based on a novel, gamma ladder variational autoencoder (VAE) architecture.  ...  We report both quantitative and qualitative results on several benchmark datasets and compare our model with several state-of-the-art methods.  ...  We refer to our model as LGVG (Ladder Gamma Variational Autoencoder for Graphs) and its version with side-information as LGVG-X.  ... 
doi:10.1609/aaai.v34i04.6013 fatcat:be2y5orhzbhntd5oeckulc5wtm
« Previous Showing results 1 — 15 out of 10,956 results