Filters








26,863 Hits in 6.3 sec

Continuous-Time Dynamic Network Embeddings

Giang Hoang Nguyen, John Boaz Lee, Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh, Sungchul Kim
2018 Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18  
The framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks.  ...  dynamics of the network.  ...  The framework provides a basis for generalizing existing random walk-based embedding methods for learning dynamic (time-dependent) network embeddings from continuous-time dynamic networks.  ... 
doi:10.1145/3184558.3191526 dblp:conf/www/NguyenLRAKK18 fatcat:c57uz7xqereczhtvghak66apbq

dynnode2vec: Scalable Dynamic Network Embedding [article]

Sedigheh Mahdavi, Shima Khoshraftar, Aijun An
2019 arXiv   pre-print
In order to tackle these challenges, dynnode2vec uses evolving random walks and initializes the current graph embedding with previous embedding vectors.  ...  In this paper, we propose a dynamic embedding method, dynnode2vec, based on the well-known graph embedding method node2vec. Node2vec is a random walk based embedding method for static networks.  ...  ACKNOWLEDGEMENTS We would like to thank Palash Goyal for kindly sharing the source code for the DynGEM method.  ... 
arXiv:1812.02356v2 fatcat:iegp5huzqfdqzk5axe2grttybi

A Survey on Dynamic Network Embedding [article]

Yu Xie, Chunyi Li, Bin Yu, Chen Zhang, Zhouhua Tang
2020 arXiv   pre-print
and the temporal dynamics, which is beneficial to multifarious downstream machine learning tasks.  ...  Compared to widely proposed static network embedding methods, dynamic network embedding endeavors to encode nodes as low-dimensional dense representations that effectively preserve the network structures  ...  Acknowledgement The authors wish to thank the editors and anonymous reviewers for their valuable comments and helpful suggestions which greatly improved the paper's quality.  ... 
arXiv:2006.08093v1 fatcat:3t7ma6zp4rhy5csilzbuwm6k7y

Node embeddings in dynamic graphs

Ferenc Béres, Domokos M. Kelen, Róbert Pálovics, András A. Benczúr
2019 Applied Network Science  
Most of the known techniques extract embeddings from static graph snapshots. By contrast, modeling the dynamics of the nodes in temporal networks requires evolving node representations.  ...  To evaluate our methods, in addition to the standard link prediction task, we provide dynamic ground truth data for the quantitative evaluation of similarity search by using online updated node embeddings  ...  Temporal walk sampling from edge stream Given a node v, a naive idea would be to compute the walk weight {p(z, t) : z is a temporal walk from w to v} for all other nodes w and set the embedding of w close  ... 
doi:10.1007/s41109-019-0169-5 fatcat:2bwsewieobbg7hkrd2qu3wmnmi

GloDyNE: Global Topology Preserving Dynamic Network Embedding [article]

Chengbin Hou, Han Zhang, Shan He, Ke Tang
2020 arXiv   pre-print
The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step.  ...  Learning low-dimensional topological representation of a network in dynamic environments is attracting much attention due to the time-evolving nature of many real-world networks.  ...  ACKNOWLEDGMENTS We would like to thank all anonymous reviewers for their constructive comments. This work was supported in part by the National Key  ... 
arXiv:2008.01935v2 fatcat:e6xwnrqm5zh5veevdgqekq4pka

Dynamic Node Embeddings from Edge Streams [article]

John Boaz Lee, Giang Nguyen, Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh, Sungchul Kim
2020 arXiv   pre-print
In this work, we propose using the notion of temporal walks for learning dynamic embeddings from temporal networks.  ...  Unlike previous work, CTDNEs learn dynamic node embeddings directly from the temporal network at the finest temporal granularity and thus use only temporally valid information.  ...  Temporal Random Walks After selecting the initial edge e i = (u, v, t) at time t to begin the temporal random walk (Section IV-A) using F s , how can we perform a temporal random walk starting from that  ... 
arXiv:1904.06449v2 fatcat:nmfuo63f2zdbfkf6v7on235gsu

DyANE: Dynamics-aware node embedding for temporal networks [article]

Koya Sato, Mizuki Oka, Alain Barrat, Ciro Cattuto
2020 arXiv   pre-print
We achieve this by using a modified supra-adjacency representation of temporal networks and building on standard embedding techniques for static graphs based on random-walks.  ...  We show that the resulting embedding vectors are useful for prediction tasks related to paradigmatic dynamical processes, namely epidemic spreading over empirical temporal networks.  ...  We will consider embeddings based on random walks as they explore the temporal paths on which transmission between nodes can occur.  ... 
arXiv:1909.05976v2 fatcat:55y64ijcfjas3mcfqkf22oud7q

Multi-View Dynamic Heterogeneous Information Network Embedding [article]

Zhenghao Zhang, Jianbin Huang, Qinglin Tan
2020 arXiv   pre-print
To tackle above challenges, we propose a novel framework for incorporating temporal information into HIN embedding, denoted as Multi-View Dynamic HIN Embedding (MDHNE), which can efficiently preserve evolution  ...  Although several dynamic embedding methods have been proposed, they are merely designed for homogeneous networks and cannot be directly applied in heterogeneous environment.  ...  This method first applies random walk to generate sequences of nodes from the network, and then uses it as input to the skip-gram model to learn representations.  ... 
arXiv:2011.06346v1 fatcat:lqgpdlvzezevjjjc54zek5sbpa

FILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings [article]

Piotr Bielak, Kamil Tagowski, Maciej Falkiewicz, Tomasz Kajdanowicz, Nitesh V. Chawla
2020 arXiv   pre-print
To that end, we propose the Framework for Incremental Learning of Dynamic Networks Embedding (FILDNE), which can utilize any existing static representation learning method for learning node embeddings,  ...  with respect to the contemporary methods for representation learning on dynamic graphs.  ...  Continuous-Time Dynamic Network Embedding (CTDNE) [27] introduced temporal walks that traverse edges according to their timestamps instead of performing random-walks statically.  ... 
arXiv:1904.03423v2 fatcat:7vnfj44ncrbvndzrnoom7n32fa

Learning Dynamic Preference Structure Embedding From Temporal Networks [article]

Tongya Zheng, Zunlei Feng, Yu Wang, Chengchao Shen, Mingli Song, Xingen Wang, Xinyu Wang, Chun Chen, Hao Xu
2021 arXiv   pre-print
In the second stage, an additional attention layer is designed to fuse two sampled temporal subgraphs of a node, generating temporal node embeddings for downstream tasks.  ...  The challenges of mining temporal networks are thus two-fold: the dynamic structure of networks and the dynamic node preferences.  ...  CTDNE [19] generates a final hidden embedding for each node with temporal random walks. HTNE [7] firstly introduces the Hawkes process in temporal network modeling.  ... 
arXiv:2111.11886v1 fatcat:iq2mdgfsf5a7resoakpm22w6v4

Multiscale dynamical embeddings of complex networks [article]

Michael T. Schaub and Jean-Charles Delvenne and Renaud Lambiotte and Mauricio Barahona
2019 arXiv   pre-print
., projecting nodes onto a low dimensional space that captures dynamic similarity at different time scales, and (ii)~how to exploit our embeddings to uncover functional modules.  ...  We further highlight how certain ideas from community detection can be generalized and linked to Control Theory, by using the here developed dynamical perspective.  ...  This includes all customary defined diffusion dynamics on undirected graphs like the continuous-time unbiased random walk, the combinatorial Laplacian random walk, or the maximum entropy random walk [  ... 
arXiv:1804.03733v2 fatcat:fhpo7bcnzvg4llgtk5r4eusenu

Dynamic network embedding via incremental skip-gram with negative sampling

Hao Peng, Jianxin Li, Hao Yan, Qiran Gong, Senzhang Wang, Lin Liu, Lihong Wang, Xiang Ren
2020 Science China Information Sciences  
To address this issue, we present an efficient incremental skip-gram algorithm with negative sampling for dynamic network embedding, and provide a set of theoretical analyses to characterize the performance  ...  We also demonstrate the correctness of the theoretical analysis and the practical usefulness of the dynamic network embedding.  ...  the random walk steps in one round, and T regers to the random walk times for each vertex.  ... 
doi:10.1007/s11432-018-9943-9 fatcat:q3md7ts2yfgy3chgbrf3mlvoie

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

Yuanfu Lu, Xiao Wang, Chuan Shi, Philip S. Yu, Yanfang Ye
2019 arXiv   pre-print
Both micro- and macro-dynamics are the key factors to network evolution; however, how to elegantly capture both of them for temporal network embedding, especially macro-dynamics, has not yet been well  ...  In this paper, we propose a novel temporal network embedding method with micro- and macro-dynamics, named M^2DNE.  ...  Inspired by word2vec [18] , random walk based methods [9, 21] have been proposed to learn node embeddings by the skipgram model.  ... 
arXiv:1909.04246v1 fatcat:7peedjbktre4lmskb42aldwuqm

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.  ...  Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors.  ...  ., 2018) employed a temporal version of traditional random walks to capture temporally evolving neighborhood information.  ... 
arXiv:2010.14047v1 fatcat:g6ohpmzuzzaa3f2ifowxg2p57a

Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)

Koya Sato, Mizuki Oka, Alain Barrat, Ciro Cattuto
2021 EPJ Data Science  
We achieve this by using a lossless modified supra-adjacency representation of temporal networks and building on standard embedding techniques for static graphs based on random walks.  ...  We show that the resulting embedding vectors are useful for prediction tasks related to paradigmatic dynamical processes, namely epidemic spreading over empirical temporal networks.  ...  We will consider embeddings based on random walks as they explore the temporal paths on which transmission between nodes can occur.  ... 
doi:10.1140/epjds/s13688-021-00277-8 doaj:98a05955517141bc8d9d413d1a726ce8 fatcat:kig3otolenbkxhzsd7gjpkapnm
« Previous Showing results 1 — 15 out of 26,863 results