A Scalable Redefined Stochastic Blockmodel

2021 ◽  
Vol 15 (3) ◽  
pp. 1-28
Author(s):  
Xueyan Liu ◽  
Bo Yang ◽  
Hechang Chen ◽  
Katarzyna Musial ◽  
Hongxu Chen ◽  
...  
Keyword(s):  
Large Scale ◽  
Network Science ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Real World Data ◽  
Computational Overhead ◽  
Stochastic Blockmodel ◽  
Np Hard Problem ◽  
Large Scale Networks ◽  
The Cost

Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability. 1

scholarly journals Research on Efficient Deep Learning Algorithm Based on ShuffleGhost in the Field of Virtual Reality

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Bangtong Huang ◽  
Hongquan Zhang ◽  
Zihong Chen ◽  
Lingling Li ◽  
Lihua Shi
Keyword(s):  
Virtual Reality ◽  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
Feature Maps ◽  
Embedded Devices ◽  
Feature Map ◽  
Deep Learning Algorithm ◽  
Proper Design ◽  
The Cost

Deep learning algorithms are facing the limitation in virtual reality application due to the cost of memory, computation, and real-time computation problem. Models with rigorous performance might suffer from enormous parameters and large-scale structure, and it would be hard to replant them onto embedded devices. In this paper, with the inspiration of GhostNet, we proposed an efficient structure ShuffleGhost to make use of the redundancy in feature maps to alleviate the cost of computations, as well as tackling some drawbacks of GhostNet. Since GhostNet suffers from high computation of convolution in Ghost module and shortcut, the restriction of downsampling would make it more difficult to apply Ghost module and Ghost bottleneck to other backbone. This paper proposes three new kinds of ShuffleGhost structure to tackle the drawbacks of GhostNet. The ShuffleGhost module and ShuffleGhost bottlenecks are utilized by the shuffle layer and group convolution from ShuffleNet, and they are designed to redistribute the feature maps concatenated from Ghost Feature Map and Primary Feature Map. Besides, they eliminate the gap of them and extract the features. Then, SENet layer is adopted to reduce the computation cost of group convolution, as well as evaluating the importance of the feature maps which concatenated from Ghost Feature Maps and Primary Feature Maps and giving proper weights for the feature maps. This paper conducted some experiments and proved that the ShuffleGhostV3 has smaller trainable parameters and FLOPs with the ensurance of accuracy. And with proper design, it could be more efficient in both GPU and CPU side.

Design of Structural Health Monitoring System Based on WSNs

2014 ◽  
Vol 681 ◽  
pp. 47-50
Author(s):  
Yue Zhou ◽  
Shuai Liu ◽  
Li Xin Zhang
Keyword(s):  
Structural Health Monitoring ◽  
Monitoring System ◽  
Health Monitoring ◽  
Large Scale ◽  
State Of The Art ◽  
Health Monitoring System ◽  
Structural Health ◽  
Structural Health Monitoring System ◽  
Large Scale Networks ◽  
Monitoring Application

The structural health monitoring technology has been one of the most important issues. In this paper, the design of wireless sensor network for structural health monitoring application is studied. The basic concept, significance, state of the art of structural health monitoring, the architecture and the principle of the wireless structural health monitoring system are described. The hardware and software of the overall system are designed and built. The WLANonSAN architecture network is particularly proposed as a solution for the large-scale networks.

Unsupervised acquisition of entailment relations from the Web

2013 ◽  
Vol 21 (1) ◽  
pp. 3-47 ◽  
Author(s):  
IDAN SZPEKTOR ◽  
HRISTO TANEV ◽  
IDO DAGAN ◽  
BONAVENTURA COPPOLA ◽  
MILEN KOUYLEKOV
Keyword(s):  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
High Coverage ◽  
Web Based ◽  
Rule Acquisition ◽  
Learning Rules ◽  
Entailment Relation ◽  
Entailment Relations ◽  
The Web

AbstractEntailment recognition is a primary generic task in natural language inference, whose focus is to detect whether the meaning of one expression can be inferred from the meaning of the other. Accordingly, many NLP applications would benefit from high coverage knowledgebases of paraphrases and entailment rules. To this end, learning such knowledgebases from the Web is especially appealing due to its huge size as well as its highly heterogeneous content, allowing for a more scalable rule extraction of various domains. However, the scalability of state-of-the-art entailment rule acquisition approaches from the Web is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations. We focus on increased scalability and generality with respect to prior work, with the potential of a large-scale Web-based knowledgebase. Our algorithm takes as its input a lexical–syntactic template and searches the Web for syntactic templates that participate in an entailment relation with the input template. Experiments show promising results, achieving performance similar to a state-of-the-art unsupervised algorithm, operating over an offline corpus, but with the benefit of learning rules for different domains with no additional effort.

scholarly journals Toward a science of translational science

2017 ◽  
Vol 1 (4) ◽  
pp. 253-255 ◽  
Author(s):  
Caleb Smith ◽  
Roohi Baveja ◽  
Teri Grieb ◽  
George A. Mashour
Keyword(s):  
Translational Research ◽  
Large Scale ◽  
Network Science ◽  
Systematic Investigation ◽  
Industrial Engineering ◽  
Translational Science ◽  
Exponential Increase ◽  
Large Scale Networks ◽  
The Impact

Translational research as a discipline has experienced explosive growth over the last decade as evidenced by significant federal investment and the exponential increase in related publications. However, narrow project-focused or process-based measurement approaches have resulted in insufficient techniques to measure the translational progress of institutions or large-scale networks. A shift from traditional industrial engineering approaches to systematic investigation using the techniques of scientometrics and network science will be required to assess the impact of investments in translational research.

Offloading as a Service Middleware for Mobile Cloud Apps

2020 ◽  
Vol 10 (2) ◽  
pp. 36-55 ◽  
Author(s):  
Hamid A Jadad ◽  
Abderezak Touzene ◽  
Khaled Day
Keyword(s):  
Large Scale ◽  
Lower Cost ◽  
Performance Metrics ◽  
State Of The Art ◽  
Mobile App ◽  
Minimum Number ◽  
Computing Platforms ◽  
Load Balancing Algorithm ◽  
The Cost ◽  
Multiple Load

Recently, much research has focused on the improvement of mobile app performance and their power optimization, by offloading computation from mobile devices to public cloud computing platforms. However, the scalability of these offloading services on a large scale is still a challenge. This article describes a solution to this scalability problem by proposing a middleware that provides offloading as a service (OAS) to large-scale implementation of mobile users and apps. The proposed middleware OAS uses adaptive VM allocation and deallocation algorithms based on a CPU rate prediction model. Furthermore, it dynamically schedules the requests using a load-balancing algorithm to ensure meeting QoS requirements at a lower cost. The authors have tested the proposed algorithm by conducting multiple simulations and compared our results with state-of-the-art algorithms based on various performance metrics under multiple load conditions. The results show that OAS achieves better response time with a minimum number of VMs and reduces 50% of the cost compared to existing approaches.

Large-Scale Multi-modal Distance Metric Learning with Application to Content-Based Information Retrieval and Image Classification

2020 ◽  
Vol 34 (13) ◽  
pp. 2050034
Author(s):  
Ali Salim Rasheed ◽  
Davood Zabihzadeh ◽  
Sumia Abdulhussien Razooqi Al-Obaidi
Keyword(s):  
Information Retrieval ◽  
Image Classification ◽  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Metric Learning ◽  
Random Projection ◽  
Linear Projection ◽  
Modal Data ◽  
Related Data

Metric learning algorithms aim to make the conceptually related data items closer and keep dissimilar ones at a distance. The most common approach for metric learning on the Mahalanobis method. Despite its success, this method is limited to find a linear projection and also suffer from scalability respecting both the dimensionality and the size of input data. To address these problems, this paper presents a new scalable metric learning algorithm for multi-modal data. Our method learns an optimal metric for any feature set of the multi-modal data in an online fashion. We also combine the learned metrics with a novel Passive/Aggressive (PA)-based algorithm which results in a higher convergence rate compared to the state-of-the-art methods. To address scalability with respect to dimensionality, Dual Random Projection (DRP) is adopted in this paper. The present method is evaluated on some challenging machine vision datasets for image classification and Content-Based Information Retrieval (CBIR) tasks. The experimental results confirm that the proposed method significantly surpasses other state-of-the-art metric learning methods in most of these datasets in terms of both accuracy and efficiency.

IMPLEMENTING BACK-PROPAGATION- THROUGH-TIME LEARNING ALGORITHM USING CELLULAR NEURAL NETWORKS

1999 ◽  
Vol 09 (06) ◽  
pp. 1041-1074 ◽  
Author(s):  
TAO YANG ◽  
LEON O. CHUA
Keyword(s):  
Real Time ◽  
Time Complexity ◽  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Back Propagation ◽  
Cellular Neural Network ◽  
Small Scale ◽  
Von Neumann ◽  
On Line

In a programmable (multistage) cellular neural network (CNN) structure, the CPU is a CNN universal chip which supports massively parallel computations on patterns and images, including videos. In this paper, we decompose the structure of a class of simultaneous recurrent networks (SRN) into a CNN program and run it on a von Neumann-like stored program CNN structure. To train the SRN, we map the back-propagation-through-time (BTT) learning algorithm into a sequence of CNN subroutines to achieve real-time performance via a CNN universal chip. By computing in parallel, the CNN universal chip can be programmed to implement in real time the BTT learning algorithm, which has a very high time complexity. An estimate of the time complexity of the BTT learning algorithm based on the CNN universal chip is presented. For small-scale problems, our simulation results show that a CNN implementation of the BTT learning algorithm for a two-dimensional SRN is at least 10,000 times faster than that based on state-of-the-art sequential workstations. For the few large-scale problems which we have so far simulated, the CNN implemented BTT learning algorithm maintained virtually the same time complexity with a learning time of a few seconds, while those implemented on state-of-the-art sequential workstations dramatically increased their time complexity, often requiring several days of running time. Several examples are presented to demonstrate how efficiently a CNN universal chip can speed up the learning algorithm for both off-line and on-line applications.

scholarly journals An Effective Algorithm to Find a Cost Minimizing Gateway Deployment for Node-Replaceable Wireless Sensor Networks

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1732
Author(s):  
Sun-Ho Choi ◽  
Yoonkyung Jang ◽  
Hyowon Seo ◽  
Bum Il Hong ◽  
Intae Ryoo
Keyword(s):  
Large Scale ◽  
Computation Time ◽  
Sensor Nodes ◽  
Divide And Conquer ◽  
Divide And Conquer Algorithm ◽  
Computational Speed ◽  
Large Scale Networks ◽  
Gateway Deployment ◽  
The Cost ◽  
The Given

In this paper, we present an efficient way to find a gateway deployment for a given sensor network topology. We assume that the expired sensors and gateways can be replaced and the locations of the gateways are chosen among the given sensor nodes. The objective is to find a gateway deployment that minimizes the cost per unit time, which consists of the maintenance and installation costs. The proposed algorithm creates a cost reference and uses it to find the optimal deployment via a divide and conquer algorithm. Comparing all cases is the most reliable way to find the optimal gateway deployment, but this is practically impossible to calculate, since its computation time increases exponentially as the number of nodes increases. The method we propose increases linearly, and so is suitable for large scale networks. Additionally, compared to stochastic algorithms such as the genetic algorithm, this methodology has advantages in computational speed and accuracy for a large number of nodes. We also verify our methodology through several numerical experiments.

scholarly journals Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles

2019 ◽  
Vol 33 ◽  
pp. 8545-8552 ◽  
Author(s):  
Dahun Kim ◽  
Donghyeon Cho ◽  
In So Kweon
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
State Of The Art ◽  
Representation Learning ◽  
Space Time ◽  
Temporal Relation ◽  
Still Images ◽  
Video Frames ◽  
Spatio Temporal ◽  
The Cost

Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream of study extends to video domain where the cost of human labeling is even more expensive. However, the most of existing methods are still based on 2D CNN architectures that can not directly capture spatio-temporal information for video applications. In this paper, we introduce a new self-supervised task called as Space-Time Cubic Puzzles to train 3D CNNs using large scale video dataset. This task requires a network to arrange permuted 3D spatio-temporal crops. By completing Space-Time Cubic Puzzles, the network learns both spatial appearance and temporal relation of video frames, which is our final goal. In experiments, we demonstrate that our learned 3D representation is well transferred to action recognition tasks, and outperforms state-of-the-art 2D CNN-based competitors on UCF101 and HMDB51 datasets.

scholarly journals Active Learning Using Hint Information

2015 ◽  
Vol 27 (8) ◽  
pp. 1738-1765 ◽  
Author(s):  
Chun-Liang Li ◽  
Chun-Sung Ferng ◽  
Hsuan-Tien Lin
Keyword(s):  
Support Vector Machine ◽  
Active Learning ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Support Vector ◽  
The Novel ◽  
Real World Data ◽  
Learning Framework ◽  
Learning Tasks ◽  
Stable Performance

The abundance of real-world data and limited labeling budget calls for active learning, an important learning paradigm for reducing human labeling efforts. Many recently developed active learning algorithms consider both uncertainty and representativeness when making querying decisions. However, exploiting representativeness with uncertainty concurrently usually requires tackling sophisticated and challenging learning tasks, such as clustering. In this letter, we propose a new active learning framework, called hinted sampling, which takes both uncertainty and representativeness into account in a simpler way. We design a novel active learning algorithm within the hinted sampling framework with an extended support vector machine. Experimental results validate that the novel active learning algorithm can result in a better and more stable performance than that achieved by state-of-the-art algorithms. We also show that the hinted sampling framework allows improving another active learning algorithm designed from the transductive support vector machine.

Sign in / Sign up

Export Citation Format

Share Document