47 Hits in 4.6 sec

Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization [article]

Wei Dong, Junsheng Wu, Yi Luo, Zongyuan Ge, Peng Wang
2022 arXiv   pre-print
Our codes and supplementary materials are available at  ...  Related Work In this section, we briefly review existing work on (1) Graph Neural Networks (GNNs) and (2) Graph Contrastive Learning (GCL). Graph Neural Networks.  ...  To further improve the efficiency and scalability of our N2N network as well as ensuring the quality of selected positives, we propose a Topology-Aware Positive Sampling (TAPS) strategy, which samples  ... 
arXiv:2203.12265v1 fatcat:ffla24ughvckpo25gtmroacewy

A general backpropagation algorithm for feedforward neural networks learning

Xinghuo Yu, M.O. Efe, O. Kaynak
2002 IEEE Transactions on Neural Networks  
Sufficient conditions to guarantee the convergence of weights for time varying inputs are derived.  ...  In this letter, a general backpropagation algorithm is proposed for feedforward neural networks learning with time varying inputs.  ...  The Lyapunov function approach, which has been widely used in analyzing the stability of self-organizing neural networks such as Kohonen and Hopfield types of networks [11] , [12] , will be used to derive  ... 
doi:10.1109/72.977323 pmid:18244427 fatcat:4yovjfp7ijeldp6prtupgz73gu

Comparison of proof-of-work based blockchains against federated consensus and proof-of-validation based blockchains [article]

Ambili K. N, Jimmy Jose
2019 IACR Cryptology ePrint Archive  
proof-of-work-based blockchains, Bitcoin and Ethereum, against federated consensus-based blockchain, Ripple, and proofof-validation-based blockchain, Tendermint, along the parameters like peer to peer network  ...  and N2N [26] .  ...  Messages are broadcast over the network using P2P protocols like bitcoinj [12] . Stratum [13] is an algorithm used at mining node.  ... 
dblp:journals/iacr/NJ19a fatcat:a6ewdvlljbdi3bmxfdlnypbcye

On Federated and Proof Of Validation Based Consensus Algorithms In Blockchain

K. N. Ambili, M. Sindhu, M. Sethumadhavan
2017 IOP Conference Series: Materials Science and Engineering  
and N2N [15] .  ...  The mining process in proof of work consumes lot of electricity.  ... 
doi:10.1088/1757-899x/225/1/012198 fatcat:ptggsqqq4ze67jqaw6cv6g2teq

Supervised methods for multi-relational link prediction

Darcy Davis, Ryan Lichtenwalter, Nitesh V. Chawla
2012 Social Network Analysis and Mining  
Many important real-world systems, modeled naturally as complex networks, have heterogeneous interactions and complicated dependency structures.  ...  We develop supervised learning approaches for relationship (link) prediction in multi-relational networks, and demonstrate that a supervised approach to link prediction can enhance performance.  ...  Rooted PageRank (RPR) (Liben-Nowell and Kleinberg 2003) is another link predictor derived from the original PageRank in which prediction outputs correspond to the probability of visiting the target node  ... 
doi:10.1007/s13278-012-0068-6 fatcat:mvqo6so5rnbbhcj6nsyq6humfu

Three-dimensional displacement field of the 2010 Mw 8.8 Maule earthquake from GPS and InSAR data with the improved ESISTEM-VCE method

Luyun Xiong, Caijun Xu, Yang Liu, Yingwen Zhao, Jianghui Geng, Francisco Ortega-Culaciati
2022 Frontiers in Earth Science  
Finally, the derived vertical displacements are also compared with field investigations, indicating that the ESISTEM-VCE method can obtain more accurate weight of different datasets and perform better  ...  ., 2021) , and mining collapses (Yang et al., 2016) .  ...  (2011) described in the paper, P is the number of the RPs of the network, K i is the set of Q nearest stations in the circle centered at the i station for different data sets.  ... 
doi:10.3389/feart.2022.970493 fatcat:3hdeilaxzjev7oyydopan432zy

A two-layer network model reveals the adhesion scientist career stage and research topic in China

Yinghong Ma, Zhaoxun Ji, Le Song
2020 IEEE Access  
Here, a two-layer network model, the coauthor collaboration network(α-layer) and the paper similarity network(β-layer) with the coupled information between them, is presented, and the relationship between  ...  INDEX TERMS Two-layer network model, Markov chain, career stage, research topic, state transition. 52726 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  the ratios of E(o2n) and E(o2o) are increasing, while E(n2n) decreasing.  ... 
doi:10.1109/access.2020.2980304 fatcat:bo2p5onw45bi3fvqe6sgean4zy

Leading logarithms in the massive nonlinear sigma model

Johan Bijnens, Lisa Carloni
2010 Nuclear Physics B  
He showed that at two loops the coefficient of leading logarithm (M 2 log M 2 )2 can be deter- mined simply by performing a one-loop calculation.  ...  A given diagram has NL loops, N2n vertices with 2n legs, NI (internal) propagators and NE external legs.  ... 
doi:10.1016/j.nuclphysb.2009.10.028 fatcat:phbcggtb7bcydapdxc6jsddy4q

Energy-Efficient and Fault-Tolerant Mobile Cloud Storage

Chien-An Chen, Radu Stoleru, Geoffrey G. Xie
2016 2016 5th IEEE International Conference on Cloud Networking (Cloudnet)  
interesting from a theoretical point of view, as they pose the most challenging design settings, but also important in enabling real-world applications such as disaster relief, military operation, and mining  ...  As such, their formulations are mostly based on heuristics derived from specialized network settings, which may over-emphasize the energy efficiency and not provide sufficient protection of the stored  ...  include both military tactical cloud systems [6] [7] (there is currently an effort by the U.S. military to equip soldiers with smartphones [6] ) and civilian use cases such as disaster relief and mining  ... 
doi:10.1109/cloudnet.2016.13 dblp:conf/cloudnet/ChenSX16 fatcat:da53tib6sndnvdrmwc7jq2pnsu

Searching for empirical evidence on traffic equilibrium

Mehmet Yildirimoglu, Osman Kahraman, Peng Chen
2018 PLoS ONE  
Therefore, the firstorder derivatives are usually not available in the traffic equilibrium context.  ...  To generate travel demand, we begin by mining massive GPS records from taxis. Using the taxi trips with passengers, we identify the origin and the destination locations within the city.  ...  There are three files provided. 2 files are for the network description-links and nodes -, and 1 file is for the map-matched trajectory data.  ... 
doi:10.1371/journal.pone.0196997 pmid:29734394 pmcid:PMC5937752 fatcat:lwn6b4e6kbc6rmz2kp6ukyh4bu

A Polynomial Algorithm for Computing the Optimal Repair Strategy in a System with Independent Component Failures [article]

Sampath Srinivas
2013 arXiv   pre-print
This allows dynamic programming to be used to construct a scheme which will compute the optimal strategy with 0( n2n) network propagations. This is still exponential.  ...  This can be done by initially doing network inference with no evidence in the network.  ... 
arXiv:1302.4985v1 fatcat:chalr3hsfzg2bhwxriqzv2d3l4

SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism [article]

Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Yuanxing Ning, Phillip S. Yu, Lifang He
2021 arXiv   pre-print
This paper presents a novel hierarchical subgraph-level selection and embedding based graph neural network for graph classification, namely SUGAR, to learn more discriminative subgraph representations  ...  With the recent advances in deep learning, Graph Neural Networks (GNNs) [53] have achieved significant success in mining graph data.  ...  Sequence-to-sequence Neighbors-to-node Previous Predicted (S2S-N2N-PP) [45] , Network Structural Convolution (NEST) [58] , and MA-GCNN [35] .  ... 
arXiv:2101.08170v3 fatcat:62nxzvfqfnb75ibuoo2b432x64

Discrete and Continuous ambush games: optimal policies and approximate solutions [article]

Emmanuel Boidot, Aude Marzuoli, Eric Feron
2016 arXiv   pre-print
A parallel is drawn between the discrete problem, where the traveler moves on a network, and the continuous problem, where the traveler moves in the plane. Analytical optimal policies are derived.  ...  In order to relax the assumptions for the computation of the players' optimal strategies of the continuous game, a network is created, inspired by recently introduced sampling based motion planning techniques  ...  A linear program is formulated for the resolution of a similar ambush game on a network and the optimal strategies are derived.  ... 
arXiv:1612.02135v1 fatcat:jcnww2utebf5rp2e5zujgdgpyq

PDPM: A Patient-Defined Data Privacy Management with Nudge Theory in Decentralized E-Health Environments

Seolah JANG, Sandi RAHMADIKA, Sang Uk SHIN, Kyung-Hyune RHEE
2021 IEICE transactions on information and systems  
We use the default Ganache setting running on an RPC server HTTP://, with a network ID of 5777, and the mining status is in "automining" mode.  ...  The development has continued ever since, as evidenced in 2017 by updating the Redundant Byzantine fault tolerance, Ripple consensus bilateral node-to-node (N2N), RAFT and derivatives, Delegated Proof-ofstake  ... 
doi:10.1587/transinf.2021ngp0015 fatcat:e3nuvgyvdbhgvah75biiuamhku

Large-scale simulation of traffic flow using Markov model

Renátó Besenczi, Norbert Bátfai, Péter Jeszenszky, Roland Major, Fanny Monori, Márton Ispány, Yanyong Guo
2021 PLoS ONE  
Modeling and simulating movement of vehicles in established transportation infrastructures, especially in large urban road networks is an important task.  ...  The approach described here combines techniques which, when used together to analyze traffic on large road networks, has not previously been reported.  ...  In addition, several approaches use machine learning and data mining techniques, such as support vector regression [43] , artificial neural networks [44] [45] [46] , Bayesian networks [47] or deep  ... 
doi:10.1371/journal.pone.0246062 pmid:33561138 fatcat:cukm2ged4bg2deeg364cwotthi
« Previous Showing results 1 — 15 out of 47 results