Filters








108,904 Hits in 6.1 sec

Embedding Dynamic Attributed Networks by Modeling the Evolution Processes [article]

Zenan Xu, Zijing Ou, Qinliang Su, Jianxing Yu, Xiaojun Quan, Zhenkun Lin
2020 arXiv   pre-print
To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks.  ...  proposed methods on tracking the evolutions of dynamic networks.  ...  In this paper, a dynamic attribute network embedding model (Dane) is developed to track the evolutions of dynamic networks.  ... 
arXiv:2010.14047v1 fatcat:g6ohpmzuzzaa3f2ifowxg2p57a

Embedding Dynamic Attributed Networks by Modeling the Evolution Processes

Zenan Xu, Zijing Ou, Qinliang Su, Jianxing Yu, Xiaojun Quan, ZhenKun Lin
2020 Proceedings of the 28th International Conference on Computational Linguistics   unpublished
To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks.  ...  proposed methods on tracking the evolutions of dynamic networks. * Corresponding author.  ...  In this paper, a dynamic attribute network embedding model (Dane) is developed to track the evolutions of dynamic networks.  ... 
doi:10.18653/v1/2020.coling-main.600 fatcat:zlhorzck4jba5obtd4xtg55dq4

A Survey on Dynamic Network Embedding [article]

Yu Xie, Chunyi Li, Bin Yu, Chen Zhang, Zhouhua Tang
2020 arXiv   pre-print
dynamic networks, heterogeneous dynamic networks, dynamic attributed networks, task-oriented dynamic network embedding and more embedding spaces.  ...  Afterwards and primarily, we suggest several challenges that the existing algorithms faced and outline possible directions to facilitate the future research, such as dynamic embedding models, large-scale  ...  This work was supported by the Key Research and Development Program of Shaanxi Province (Grant no. 2019ZDLGY17-01, 2019GY-042).  ... 
arXiv:2006.08093v1 fatcat:3t7ma6zp4rhy5csilzbuwm6k7y

DEDGCN: Dual Evolving Dynamic Graph Convolutional Network

Fengzhe Zhong, Yan Liu, Lian Liu, Guangsheng Zhang, Shunran Duan
2022 Security and Communication Networks  
On the other hand, most dynamic graph neural networks require learn node embeddings from specific tasks, resulting in poor universality of node embeddings and cannot be used in unsupervised tasks.  ...  , forming an adaptive dynamic graph convolution network.  ...  First of all, we learn the evolution law of the normal AS network through DEDGCN. en, the AS network to be detected is input into the trained model to obtain the node embedding and node evolution results  ... 
doi:10.1155/2022/6945397 doaj:cd7d4d5dfe83422da30e12c67c98b833 fatcat:dr5zszfvqvg4ngvm4a6l567moa

A Survey on Embedding Dynamic Graphs [article]

Claudio D. T. Barros, Matheus R. F. Mendonça, Alex B. Vieira, Artur Ziviani
2021 arXiv   pre-print
We further explore different dynamic behaviors that may be encompassed by embeddings, classifying by topological evolution, feature evolution, and processes on networks.  ...  However, many real-world networks present dynamic behavior, including topological evolution, feature evolution, and diffusion.  ...  Acknowledgment This work has been partially supported by CAPES, CNPq, FAPEMIG, and FAPERJ.  ... 
arXiv:2101.01229v2 fatcat:lqjkkksn45g7beizhcstakf6ry

Learning Attribute-Structure Co-Evolutions in Dynamic Graphs [article]

Daheng Wang, Zhihan Zhang, Yihong Ma, Tong Zhao, Tianwen Jiang, Nitesh V. Chawla, Meng Jiang
2020 arXiv   pre-print
Most graph neural network models learn embeddings of nodes in static attributed graphs for predictive analysis. Recent attempts have been made to learn temporal proximity of the nodes.  ...  It preserves the impact of earlier graphs on the current graph by embedding generation through the sequence.  ...  ACKNOWLEDGMENTS This work was supported in part by NSF Grant IIS-1849816.  ... 
arXiv:2007.13004v1 fatcat:2lqeepd4vrgx7nfxwcazjvg7k4

Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey [article]

Yuecai Zhu, Fuyuan Lyu, Chengming Hu, Xi Chen, Xue Liu
2022 arXiv   pre-print
However, the temporal information embedded in the dynamic graphs brings new challenges in analyzing and deploying them.  ...  In order to offer a convenient reference to both the industry and academia, this survey presents the Three Stages Recurrent Temporal Learning Framework based on dynamic graph evolution theories, so as  ...  CTDG learning algorithm aims to learn the network evolution embedded in the events stream.  ... 
arXiv:2203.10480v2 fatcat:tf7n73rhtbbcpptbn6lyvhcew4

SPAN: Subgraph Prediction Attention Network for Dynamic Graphs [article]

Yuan Li, Chuanchang Chen, Yubo Tao, Hai Lin
2021 arXiv   pre-print
A new mechanism named cross-attention with a twin-tower module is designed to integrate node attribute information and topology information collaboratively for learning subgraph evolution.  ...  This paper proposes a novel model for predicting subgraphs in dynamic graphs, an extension of traditional link prediction.  ...  Acknowledgements This work was supported by National Natural Science Foundation of China (61972343).  ... 
arXiv:2108.07776v1 fatcat:s34vnwv7yvhkbnylsevsfccoja

GRADE: Graph Dynamic Embedding [article]

Simeon Spasov, Alessandro Di Stefano, Pietro Lio, Jian Tang
2021 arXiv   pre-print
Existing approaches for modelling graph dynamics focus extensively on the evolution of individual nodes independently of the evolution of mesoscale community structures.  ...  We parametrize the node and community distributions with neural networks and learn their parameters via variational inference.  ...  processes temporal point processes have also been used in combination with neural network parametrization by KnowEvolve [24] and DyREP [25] to model continuous-time node interactions in multi-relational  ... 
arXiv:2007.08060v3 fatcat:ceiicjx5wvctbklgfbizirrnqq

Pre-Training on Dynamic Graph Neural Networks [article]

Ke-jia Chen, Jiajun Zhang, Linpu Jiang, Yunyun Wang, Yuxuan Dai
2022 arXiv   pre-print
The pre-training on the graph neural network model can learn the general features of large-scale networks or networks of the same type by self-supervised methods, which allows the model to work even when  ...  This paper proposes a pre-training method on dynamic graph neural networks (PT-DGNN), which uses dynamic attributed graph generation tasks to simultaneously learn the structure, semantics, and evolution  ...  It is also a dynamic network embedding model, introducing the Hawkes process theory. It is based on the fact that the influence of neighbors on the central nodes decays over time. GPT-GNN [8] .  ... 
arXiv:2102.12380v2 fatcat:4wcmhk2vfng5dehdkuxmlxae7m

Neural Framework for Joint Evolution Modeling of User Feedback and Social Links in Dynamic Social Networks

Peizhi Wu, Yi Tu, Xiaojie Yuan, Adam Jatowt, Zhenglu Yang
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
The framework considers the dynamic user preferences, dynamic item attributes, and time-dependent social links in time evolving social networks.  ...  Most of the existing methods in this area model user behaviors separately and consider only certain aspects of this problem, such as dynamic preferences of users, dynamic attributes of items, evolutions  ...  Acknowledgements This work was supported in part by the National Natural Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2018/226 dblp:conf/ijcai/WuTYJY18 fatcat:gdy7aou3pzdezcaxygdrky7hmy

Toward Digital Twin Oriented Modeling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Jiaqi Wen, Bogdan Gabrys, Katarzyna Musial
2022 IEEE Access  
INDEX TERMS Complex network systems, digital twins, dynamic processes, network dynamics.  ...  We propose four complexity dimensions for the network representation and five generations of models for the dynamics modelling to describe the increasing complexity level of the CNS that will be developed  ...  From a global view, more complex models can embed more complex networked information but are characterised by less interpretable embedding process and inference results, such as the network embedding paradigms  ... 
doi:10.1109/access.2022.3184801 fatcat:q7glnphnobbkxforsqbafpgbri

DyEgoVis: Visual Exploration of Dynamic Ego-Network Evolution

Kun Fu, Tingyun Mao, Yang Wang, Daoyu Lin, Yuanben Zhang, Xian Sun
2021 Applied Sciences  
Exploring dynamic ego-networks can help users gain insight into how each ego interacts with and is influenced by the outside world.  ...  However, most of the existing methods do not fully consider the multilevel analysis of dynamic ego-networks, resulting in some evolution information at different granularities being ignored.  ...  Acknowledgments: The authors would like to thank all the colleagues for the fruitful discussions on dynamic network visualization. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app11052399 fatcat:alck2fwpcjg3bplqvucmxdwy5e

DyRep: Learning Representations over Dynamic Graphs

Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha
2019 International Conference on Learning Representations  
as topological evolution) and dynamics on the network (realized as activities between nodes).  ...  This model is further parameterized by a temporal-attentive representation network that encodes temporally evolving structural information into node representations which in turn drives the nonlinear evolution  ...  This work was supported in part by NSF IIS-1717916, NSF CMMI-1745382, NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Information (U1609220) and National Science Foundation of China  ... 
dblp:conf/iclr/TrivediFBZ19 fatcat:z6og4ca52rawpmj2bnubg7vdfq

Temporal Network Embedding with Micro- and Macro-dynamics [article]

Yuanfu Lu, Xiao Wang, Chuan Shi, Philip S. Yu, Yanfang Ye
2019 arXiv   pre-print
Mutual evolutions of micro- and macro-dynamics in a temporal network alternately affect the process of learning node embeddings.  ...  The micro-dynamics describe the formation process of network structures in a detailed manner, while the macro-dynamics refer to the evolution pattern of the network scale.  ...  The Unified Model As micro-and macro-dynamics mutually drive the evolution of the temporal network, which alternately influence the learning process of network embeddings, we have the following model to  ... 
arXiv:1909.04246v1 fatcat:7peedjbktre4lmskb42aldwuqm
« Previous Showing results 1 — 15 out of 108,904 results