Filters








15,323 Hits in 6.5 sec

Network Distance Prediction Based on Decentralized Matrix Factorization [chapter]

Yongjun Liao, Pierre Geurts, Guy Leduc
2010 Lecture Notes in Computer Science  
The former is based on metric space embedding, while the latter is also based on matrix factorization but uses landmarks.  ...  To overcome these drawbacks, we formulate the problem of network distance prediction as guessing the missing elements of a distance matrix and solve it by matrix factorization.  ...  Acknowledgements This work has been partially supported by the EU under projects FP7-Fire ECODE, by the European Network of Excellence PASCAL2 and by the Belgian network DYSCO (Dynamical Systems, Control  ... 
doi:10.1007/978-3-642-12963-6_2 fatcat:2mxqaw3x6zfdheblfkwwein7qm

DMFSGD: A Decentralized Matrix Factorization Algorithm for Network Distance Prediction

Yongjun Liao, Wei Du, Pierre Geurts, Guy Leduc
2013 IEEE/ACM Transactions on Networking  
A new algorithm, so-called Decentralized Matrix Factorization by Stochastic Gradient Descent (DMFSGD), is proposed to solve the network distance prediction problem.  ...  In addition, we compared comprehensively matrix factorization and Euclidean embedding to demonstrate the suitability of the former on network distance prediction.  ...  ACKNOWLEDGMENTS This work was partially supported by the EU under project FP7-Fire ECODE, by the European Network of Excellence PASCAL2 and by the Belgian network DYSCO (Dynamical Systems, Control, and  ... 
doi:10.1109/tnet.2012.2228881 fatcat:lc4vsrlocreyjogsvmgaxiimzi

Phoenix: A Weight-Based Network Coordinate System Using Matrix Factorization

Yang Chen, Xiao Wang, Cong Shi, Eng Keong Lua, Xiaoming Fu, Beixing Deng, Xing Li
2011 IEEE Transactions on Network and Service Management  
In this paper, we propose an NC system, so-called Phoenix, which is based on the matrix factorization model.  ...  Network coordinate (NC) systems provide a lightweight and scalable way for predicting the distances, i.e., round-trip latencies among Internet hosts.  ...  We design and implement a fully decentralized matrix factorization based NC system, so-called Phoenix.  ... 
doi:10.1109/tnsm.2011.110911.100079 fatcat:i74yzmpvgzbb3ejwdgaakgu7lm

Phoenix: Towards an Accurate, Practical and Decentralized Network Coordinate System [chapter]

Yang Chen, Xiao Wang, Xiaoxiao Song, Eng Keong Lua, Cong Shi, Xiaohan Zhao, Beixing Deng, Xing Li
2009 Lecture Notes in Computer Science  
Network coordinate (NC) system allows efficient Internet distance prediction with scalable measurements. Most of the NC systems are based on embedding hosts into a low dimensional Euclidean space.  ...  However, it cannot guarantee the predicted distance non-negative and its prediction accuracy is close to the Euclidean distance based NC systems.  ...  The key idea of this system is that a large distance matrix can be approximately factorized into two smaller matrices by methods like Singular Value Decomposition (SVD) or Non-negative Matrix Factorization  ... 
doi:10.1007/978-3-642-01399-7_25 fatcat:6fyotrmqvvep5o32cpjmctrdyq

Improving Prediction Accuracy of Matrix Factorization Based Network Coordinate Systems

Yang Chen, Peng Sun, Xiaoming Fu, Tianyin Xu
2010 2010 Proceedings of 19th International Conference on Computer Communications and Networks  
To overcome the problem of TIV, matrix factorization (MF) based NC systems such as IDES [7] , Phoenix [1] and DMF [5] have been developed.  ...  INTRODUCTION Network Coordinate (NC) systems provide a lightweight and useful way for scalable Internet distance prediction.  ... 
doi:10.1109/icccn.2010.5560092 dblp:conf/icccn/ChenSFX10 fatcat:w5rlqihr5zgt3kbr7g7lb6islq

Decentralized prediction of end-to-end network performance classes

Yongjun Liao, Wei Du, Pierre Geurts, Guy Leduc
2011 Proceedings of the Seventh COnference on emerging Networking EXperiments and Technologies on - CoNEXT '11  
We propose a decentralized approach based on Stochastic Gradient Descent to solve this class-based matrix completion problem.  ...  Under this framework, we formulate the prediction problem as matrix completion, whereby unknown entries of an incomplete matrix of pairwise measurements are to be predicted.  ...  This work was partially supported by the EU under project FP7-Fire ECODE, by the European Network of Excellence PAS-CAL2 and by the Belgian network DYSCO (Dynamical Systems, Control, and Optimization),  ... 
doi:10.1145/2079296.2079310 dblp:conf/conext/LiaoDGL11 fatcat:tq5uektxivh4tieg2urv2rqq74

A general scalable and accurate decentralized level monitoring method for large-scale dynamic service provision in hybrid clouds

Yongquan Fu, Yijie Wang, Ernst Biersack
2013 Future generations computer systems  
Each node independently maintains its low-dimensional coordinate based on a novel decentralized implementation of the Maximum Margin Matrix Factorization method that optimizes 1 1 the mapping between the  ...  HPM maps probed metric to discrete levels based on an existing distributed Kmeans clustering method that helps maximize the similarity of the network metric in the same level, which therefore optimizes  ...  Estimating the Level We define the coordinate distances based on the matrix factorization, in order to be general enough to adapt different kinds of network metric: The pairwise coordinate distance is  ... 
doi:10.1016/j.future.2012.11.001 fatcat:bxp6wvoqu5attmwcnf32lbghfa

Epidemic Trust-Based Recommender Systems

Stefan Magureanu, Nima Dokoohaki, Shahab Mokarizadeh, Mihhail Matskin
2012 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing  
Collaborative filtering(CF) recommender systems are among the most popular approaches to solving the information overload problem in social networks by generating accurate predictions based on the ratings  ...  recommendations based on local information of a node.  ...  Matrix factorization-based algorithms are often employed when the data on users is very scarce and can generate more predictions than CF approaches.  ... 
doi:10.1109/socialcom-passat.2012.94 dblp:conf/socialcom/MagureanuDMM12 fatcat:ov273v4trnawtlzjz7lm44zane

NCShield: Securing decentralized, matrix factorization-based network coordinate systems

Shining Wu, Yang Chen, Xiaoming Fu, Jun Li
2012 2012 IEEE 20th International Workshop on Quality of Service  
While network coordinate (NC) systems provide scalable Internet distance estimation service and are useful for various Internet applications, decentralized, matrix factorization-based NC (MFNC) systems  ...  In this paper, we provide the first study on attacks toward MFNC systems, and propose a decentralized trust and reputation approach, called NCShield, to counter such attacks.  ...  a real network.  ... 
doi:10.1109/iwqos.2012.6245983 dblp:conf/iwqos/WuCFL12 fatcat:yqse6etwrjbfbbjanbcyujarju

Homogeneous Learning: Self-Attention Decentralized Deep Learning [article]

Yuwei Sun, Hideya Ochiai
2021 arXiv   pre-print
decentralized learning for training on non-IID data.  ...  One of the most challenging issues in decentralized deep learning is that data owned by each node are usually non-independent and identically distributed (non-IID), causing time-consuming convergence of  ...  Moreover, a fully decentralized deep learning architecture is peer-to-peer networking of nodes based on decentralization and security technologies such as the token-exchange, a service capable of validating  ... 
arXiv:2110.05290v1 fatcat:xz5c3wv2vveptbynrs3fnu4vee

An Effective and Robust Decentralized Target Tracking Scheme in Wireless Camera Sensor Networks

Pengcheng Fu, Yongbo Cheng, Hongying Tang, Baoqing Li, Jun Pei, Xiaobing Yuan
2017 Sensors  
Additionally, we design an efficient cluster head (CH) selection mechanism that casts such selection problem as an optimization problem based on the remaining energy and distance-to-target.  ...  In this paper, we propose an effective and robust decentralized tracking scheme based on the square root cubature information filter (SRCIF) to balance the energy consumption and tracking accuracy in wireless  ...  With respect to the weighting factor α i,k+1 , we set it with different values based on both the predicted position of the target and the FOV of the camera c i .  ... 
doi:10.3390/s17030639 pmid:28335537 pmcid:PMC5375925 fatcat:lo6xxdarsfczpaqscmbmq25hza

Predictive state vector encoding for decentralized field estimation in sensor networks

Florian Xaver, Gerald Matz, Peter Gerstoft, Christoph Mecklenbrauker
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Decentralized physics-based field estimation in clustered sensor networks requires the exchange of state vectors between neighboring clusters.  ...  This encoding involves a Kalman prediction step that builds on the state-space equations governing the field's spatio-temporal evolution. The Kalman step keeps the computational complexity low.  ...  Decentralized predictive encoding algorithm In the following, the subscript k|k emphasizes that estimates at time k are based on observations up to time k.  ... 
doi:10.1109/icassp.2012.6288464 dblp:conf/icassp/XaverMGM12 fatcat:e3bovwaph5gc5ju7eu4arkngr4

Distributed Coordinated Voltage Control for Distribution Networks with DG and OLTC based on MPC and Gradient Projection

Wenshu Jiao, Jian Chen, Qiuwei Wu, Sheng Huang, Canbing Li, Bin Zhou
2021 IEEE Transactions on Power Systems  
.  Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making  ...  Decentralized control based on the GP method for DG and STATCOM is presented in Section III. The OLTC control based on MPC is described in Section IV.  ...  Thus, a decentralized control scheme based on the GP is used for DG and STATCOM controllers.  ... 
doi:10.1109/tpwrs.2021.3095523 fatcat:zq6i4rhtlvaqpftytq5lkf7d6a

Decentralized Gradient-based Field Motion Estimation with a Wireless Sensor Network

Daniel Fitzner, Monika Sester
2016 Proceedings of the 5th International Confererence on Sensor Networks  
Decentralized Gradient-based Field Motion Estimation with a Wireless Sensor Network.  ...  In this paper, an algorithm for the decentralized estimation of motion of a spatio-temporal field by the nodes of a stationary and synchronized Wireless Sensor Network (WSN) is presented.  ...  Including these as well as weighting measures based on spatial distance is planned for future extensions.  ... 
doi:10.5220/0005639100130024 dblp:conf/sensornets/FitznerS16 fatcat:jafvggvrmzfo3h5m3yhlvvt2fq

On the feasibility of common-friend measurements for the distributed online social networks

Yongquan Fu, Yijie Wang
2012 7th International Conference on Communications and Networking in China  
Simulation results on real-world social networks confirm that FDist is both scalable and accurate.  ...  Distributed social networks have emerged recently. Nevertheless, recommending friends in the distributed social networks has not been exploited fully.  ...  on the matrix factorization.  ... 
doi:10.1109/chinacom.2012.6417442 dblp:conf/chinacom/FuW12 fatcat:pkdx4syl5fapheltw5k4f4itau
« Previous Showing results 1 — 15 out of 15,323 results