88 Hits in 5.1 sec

Graph Neural Networks Designed for Different Graph Types: A Survey [article]

Josephine M. Thomas and Alice Moallemy-Oureh and Silvia Beddar-Wiesing and Clara Holzhüter
2022 arXiv   pre-print
Based on this, the young research field of Graph Neural Networks (GNNs) has emerged.  ...  We consider GNNs operating on static as well as on dynamic graphs of different structural constitutions, with or without node or edge attributes.  ...  Graph Convolutional Neural Networks (GCNN) In Graph Convolutional Neural Networks, each nodes aggregates neighboring nodes using learnable weights.  ... 
arXiv:2204.03080v2 fatcat:52o4dx5ulve3na7vndmbpqhpcm

Deep-Learning-Based Community Detection Approach on Multimedia Social Networks

Antonino Ferraro, Vincenzo Moscato, Giancarlo Sperlì
2021 Applied Sciences  
This matrix was then computed in a novel way through a Convolutional Neural Network (CNN), suitably modified to handle high data sparsity, in order to generate communities among users.  ...  In particular, these networks consider new ways of interaction and further relationships among users to support various SNA tasks: influence analysis, expert finding, community identification, item recommendation  ...  structure, unknown communities, network heterogeneity, signed information on edges, community embedding, networks dynamic, etc  ... 
doi:10.3390/app112311447 fatcat:sgsnldorm5b5nbucbtyoboemv4

Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction

Hongxu Chen, Hongzhi YIN, Xiangguo Sun, Tong Chen, Bogdan Gabrys, Katarzyna Musial
2020 Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining  
In this paper, to address this problem, we propose a novel framework that considers multi-level graph convolutions on both local network structure and hypergraph structure in a unified manner.  ...  The experimental results demonstrate that the proposed method outperforms the state-of-the-art models with a big margin. CCS CONCEPTS • Information systems → Data mining.  ...  However, with the increased public awareness of privacy and information rights, these information is becoming less available and accessible.  ... 
doi:10.1145/3394486.3403201 fatcat:jx7gb6a4vnfo5d6e2kkuc3m5cq

Gaussian process decentralized data fusion meets transfer learning in large-scale distributed cooperative perception

Ruofei Ouyang, Bryan Kian Hsiang Low
2019 Autonomous Robots  
Neural Network Deepak Babu Sam*, Venkatesh Babu R.  ...  , Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh Early Detection of Fake News on Social Media Through Propagation Path Classification with Recurrent and Convolutional Networks Yang Liu*, Brook Wu Early Prediction  ... 
doi:10.1007/s10514-018-09826-z fatcat:67yqhwmgozccxni56rxmuapjgm

Graph Neural Networks: A Review of Methods and Applications [article]

Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun
2021 arXiv   pre-print
Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs.  ...  In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning  ...  Signed graphs Signed graphs are the graphs with signed edges, i.e. an edge can be either positive or negative.  ... 
arXiv:1812.08434v6 fatcat:ncz44kny6nairjjnysrqd5qjoi

Graph Neural Networks: Taxonomy, Advances and Trends [article]

Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li, Jumin Zhao
2022 arXiv   pre-print
First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 400 relevant literatures to show the panorama of the graph neural networks.  ...  This survey aims to overcome this limitation, and provide a comprehensive review on the graph neural networks.  ...  The spectral hypergraph convolution operator, the Chebyshev hypergraph convolutional neural network and the hypergraph convolutional network can be defined in analogy to Eqs (4, 6, 8) .  ... 
arXiv:2012.08752v3 fatcat:xj2kambrabfj3g5ldenfyixzu4

Temporal network embedding using graph attention network

Anuraj Mohan, K V Pramod
2021 Complex & Intelligent Systems  
AbstractGraph convolutional network (GCN) has made remarkable progress in learning good representations from graph-structured data.  ...  The layer-wise propagation rule of conventional GCN is designed in such a way that the feature aggregation at each node depends on the features of the one-hop neighbouring nodes.  ...  Researchers developed different variants to GCN which can work with more complex settings like heterogeneous networks [45, 46] , signed networks [47] , and hypergraphs [48] .  ... 
doi:10.1007/s40747-021-00332-x fatcat:jy6q2meccnbqvjhhxkdlmmhnmm

SiReN: Sign-Aware Recommendation Using Graph Neural Networks [article]

Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin
2022 arXiv   pre-print
In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy.  ...  In this study, we present SiReN, a new sign-aware recommender system based on GNN models.  ...  An approach for formulating feature-aware recommendation from the review information via a signed hypergraph convolutional network was also presented in [47] . C.  ... 
arXiv:2108.08735v2 fatcat:bd2rfl4pbbc35aj5uapy2cdhj4

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
spatially enriched pixel time series with convolutional neural networks DAY 3 -Jan 14, 2021 Liu, Hong; Wang, Yawei; Yang, Bing 1459 Mutual Alignment between Audiovisual Features for End-To-End  ...  : Quantifying the Generative Adversarial Set and Class Feature Applicability of Deep Neural Networks Deep transformation models: Tackling complex regression problems with neural network based transformation  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Community Detection Clustering via Gumbel Softmax

Deepak Bhaskar Acharya, Huaming Zhang
2020 SN Computer Science  
Graphs have gained growing traction in different fields, including social networks, information graphs, the recommender system, and also life sciences.  ...  We cluster different category datasets that belong to affiliation networks, animal networks, human contact networks, human social networks, miscellaneous networks.  ...  Gumbel Softmax Approach on Feature Selection Deepak and Huaming [1] selected Graph Neural Network(GNN) features in the paper feature selection and extraction for Graph Neural Networks, with the citation  ... 
doi:10.1007/s42979-020-00264-2 fatcat:xyzh7gmjcjbrxat3uhej2nli7q

Neuro-Symbolic Learning: Principles and Applications in Ophthalmology [article]

Muhammad Hassan, Haifei Guan, Aikaterini Melliou, Yuqi Wang, Qianhui Sun, Sen Zeng, Wen Liang, Yiwei Zhang, Ziheng Zhang, Qiuyue Hu, Yang Liu, Shunkai Shi (+15 others)
2022 arXiv   pre-print
Neural networks have been rapidly expanding in recent years, with novel strategies and applications.  ...  Attempts have been made to overcome the challenges in neural network computing by representing and embedding domain knowledge in terms of symbolic representations.  ...  MSCNN: Multiscale sequential convolutional neural networks, RPNCN: Region proposal network and cascaded network, ALMF: Adversarial learning with multiscale features, age-related eye disease study (AREDS  ... 
arXiv:2208.00374v1 fatcat:pktmnomj3bbwpjyj7lmu37rl7i

2020 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 31

2020 IEEE Transactions on Neural Networks and Learning Systems  
Yin, J., +, TNNLS Sept. 2020 3442-3455 RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems.  ...  ., +, TNNLS July 2020 2653-2664 Nonpooling Convolutional Neural Network Forecasting for Seasonal Time Series With Trends.  ...  ., +, TNNLS Oct. 2020 3777-3787 On the Working Principle of the Hopfield Neural Networks and its Equivalence to the GADIA in Optimization. Uykan, Z.,  ... 
doi:10.1109/tnnls.2020.3045307 fatcat:34qoykdtarewhdscxqj5jvovqy

2020 Index IEEE Journal of Biomedical and Health Informatics Vol. 24

2020 IEEE journal of biomedical and health informatics  
Qadir, H.A., +, JBHI Jan. 2020 180-193 Inter-Patient ECG Classification With Symbolic Representations and Multi-Perspective Convolutional Neural Networks.  ...  Pan, C., +, JBHI Feb. 2020 626-633 Convolutional Recurrent Neural Networks for Glucose Prediction.  ... 
doi:10.1109/jbhi.2020.3048808 fatcat:iifrkwtzazdmboabdqii7x5ukm

Survey of Generative Methods for Social Media Analysis [article]

Stan Matwin, Aristides Milios, Paweł Prałat, Amilcar Soares, François Théberge
2021 arXiv   pre-print
We included two important aspects that currently gain importance in mining and modeling social media: dynamics and networks.  ...  Networks, on the other hand, may capture various complex relationships providing additional insight and identifying important patterns that would otherwise go unnoticed.  ...  Signed Networks The vast majority of existing node embedding algorithms are designed for social networks without sign, typically only with positive links.  ... 
arXiv:2112.07041v1 fatcat:xgmduwctpbddfo67y6ack5s2um

Table of Contents

2020 2020 IEEE International Conference on Image Processing (ICIP)  
NEURAL NETWORKS 0LQ .  ...  ATTENTION MODEL FOR RESTAURANT .................................................................. 838 RECOMMENDATION WITH MULTI-VIEW VISUAL FEATURES +DLKXD /XR ;LDR\DQ =KDQJ 6KHQ]KHQ 8QLYHUVLW\ &KLQD  ...  REGULARISATION WITH A ...............................................  ... 
doi:10.1109/icip40778.2020.9191006 fatcat:3fkxl2sjmre2jkryewwo5mlahi
« Previous Showing results 1 — 15 out of 88 results