检索结果-内蒙古大学图书馆

29th International Conference on Scientifc and Statistical Database Management (SSDBM)

作者： Qin, Chengjie Rusu, Florin GraphSQL Inc Millbrae CA 94030 USA Univ Calif Merced Merced CA USA

ISBN: (纸本)9781450352826

Big Model analytics tackles the training of massive models that go beyond the available memory of a single computing device, e.g., CPU or GPU. It generalizes Big Data analytics which is targeted at how to train memory-resident models over out-of-memory training data. In this paper, we propose an in-database solution for Big Model analytics. We identify dot-product as the primary operation for training generalized linear models and introduce the first array-relation dot-product join database operator between a set of sparse arrays and a dense relation. This is a constrained formulation of the extensively studied sparse matrix vector multiplication (SpMV) kernel. The paramount challenge in designing the dot-product join operator is how to optimally schedule access to the dense relation based on the non-contiguous entries in the sparse arrays. We propose a practical solution characterized by two technical contributions-dynamic batch processing and array reordering. We devise three heuristics - LSH, Radix, and K-center - for array reordering and analyze them thoroughly. We execute extensive experiments over synthetic and real data that confirm the minimal overhead the operator incurs when sufficient memory is available and the graceful degradation it suffers as memory becomes scarce. Moreover, dot-product join achieves an order of magnitude reduction in execution time over alternative solutions.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Scalable asynchronous gradient descent optimization for out-of-core models 43

Scalable asynchronous gradient descent optimization for out-...

引用

43rd International Conference on Very Large Data Bases, VLDB 2017

作者： Qin, Chengjie Torres, Martin Rusu, Florin GraphSQL Inc. United States University of California Merced United States

Existing data analytics systems have approached predictive model training exclusively from a data-parallel perspective. Data examples are partitioned to multiple workers and training is executed concurrently over different partitions, under various synchronization policies that emphasize speedup or convergence. Since models with millions and even billions of features become increasingly common nowadays, model management becomes an equally important task for effective training. In this paper, we present a general framework for parallelizing stochastic optimization algorithms over massive models that cannot fit in memory. We extend the lockfree HOGWILD!-family of algorithms to disk-resident models by vertically partitioning the model offline and asynchronously updating the resulting partitions online. Unlike HOGWILD!, concurrent requests to the common model are minimized by a preemptive push-based sharing mechanism that reduces the number of disk accesses. Experimental results on real and synthetic datasets show that the proposed framework achieves improved convergence over HOGWILD! and is the only solution scalable to massive models. © 2017 VLDB Endowment.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

PREDIcT: Towards Predicting the Runtime of Large Scale Iterative Analytics

引用

PROCEEDINGS OF THE VLDB ENDOWMENT 2013年第14期6卷 1678-1689页

作者： Popescut, Adrian Daniel Balmin, Andrey Ercegoyac, Vuk Ailamaki, Anastasia Ecole Polytech Fed Lausanne CH-1015 Lausanne Switzerland IBM Almaden Res Ctr San Jose CA USA GraphSQL Mountain View CA USA Google Inc Menlo Pk CA USA

Machine learning algorithms are widely used today for analytical tasks such as data cleaning, data categorization, or data filtering. At the same time, the rise of social media motivates recent uptake in large scale graph processing. Both categories of algorithms are dominated by it er a tivesubtasks,i.e., processing steps which are executed repetitively until a convergence condition is met. Optimizing cluster resource allocations among multiple workloads of iterative algorithms motivates the need for estimating their runtime, which in turn requires: i) predicting the number of iterations, and ii) predicting the processing time of each iteration. As both parameters depend on the characteristics of the dataset and on the convergence function, estimating their values before execution is difficult.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Scalable Asynchronous Gradient Descent Optimization for Out-of-Core Models

引用

PROCEEDINGS OF THE VLDB ENDOWMENT 2017年第10期10卷 986-997页

作者： Qin, Chengjie Torres, Martin Rusu, Florin Univ Calif Merced Merced CA USA GraphSQL Inc Redwood City CA 94065 USA

Existing data analytics systems have approached predictive model training exclusively from a data-parallel perspective. Data examples are partitioned to multiple workers and training is executed concurrently over different partitions, under various synchronization policies that emphasize speedup or convergence. Since models with millions and even billions of features become increasingly common nowadays, model management becomes an equally important task for effective training. In this paper, we present a general framework for parallelizing stochastic optimization algorithms over massive models that cannot fit in memory. We extend the lock-free HOGWILD!-family of algorithms to disk-resident models by vertically partitioning the model offline and asynchronously updating the resulting partitions online. Unlike HOGWILD!, concurrent requests to the common model are minimized by a preemptive push-based sharing mechanism that reduces the number of disk accesses. Experimental results on real and synthetic datasets show that the proposed framework achieves improved convergence over HOGWILD! and is the only solution scalable to massive models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uniform-scale assessment of role minimization in bipartite networks and its application to access control

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2018年 507卷 381-397页

作者： Wu, Liuyi Dong, Lijun Wang, Yi Zhang, Feng Lee, Victor E. Kang, Xiaojun Liang, Qingzhong China Univ Geosci Sch Comp Sci Wuhan 430074 Hubei Peoples R China China Univ Geosci Hubei Key Lab Intelligent Geoinformat Proc Wuhan 430074 Hubei Peoples R China China Univ Geosci Sch Math & Phys Wuhan 430074 Hubei Peoples R China GraphSQL Inc Mountain View CA 94043 USA

As an important kind of complex network models, bipartite network is widely used in many applications such as access control. The process of finding a set of structural communities in a bipartite network is called role mining, which has been extensively used to automatically generate roles for structural communities. Role minimization, aiming to get the fewest roles to reduce the administrative complexity of the access control, is the simplest and most popular form of role mining. Current assessment metrics of role minimization results are based on the absolute values, and cannot measure or compare the results from different algorithms and different datasets on a uniform scale. To address this problem, this study proposes a framework of mark-based evaluation for role minimization (MERM) to provide a normalized measure for different role minimization results on a uniform scale. According to MERM, for each dataset, three quantitative reference marks are established to mirror the level of role minimization results. The marks are entirely determined by the inherent features of a dataset but have nothing to do with any role mining algorithm. Based on the marks, a normalized score vector is constructed to estimate the performance of results, independent of the size of any dataset. MERM can assess varieties of role minimization results on a uniform scale. The experimental results show the effectiveness of MERM: the different results generated from nine algorithms on six datasets can be measured on a uniform scale. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Complex network Bipartite network Access control Role mining Role minimization

来源：评论

学校读者我要写书评

暂无评论

Dynamically Optimizing Queries over Large Scale Data Platforms 14

Dynamically Optimizing Queries over Large Scale Data Platfor...

引用

ACM SIGMOD International Conference on Management of Data

作者： Karanasos, Konstantinos Balmin, Andrey Kutsch, Marcel Ozcan, Fatma Ercegovac, Vuk Xia, Chunyang Jackson, Jesse IBM Res Almaden San Jose CA 95120 USA GraphSQL Millbrae CA USA Apple Inc Cupertino CA USA Google Mountain View CA USA IBM Silicon Valley Lab San Jose CA USA IBM Res San Jose CA USA

ISBN: (纸本)9781450323765

Enterprises are adapting large-scale data processing platforms, such as Hadoop, to gain actionable insights from their "big data". Query optimization is still an open challenge in this environment due to the volume and heterogeneity of data, comprising both structured and un/semi-structured datasets. Moreover, it has become common practice to push business logic close to the data via user defined functions (UDFs), which are usually opaque to the optimizer, further complicating cost-based optimization. As a result, classical relational query optimization techniques do not fit well in this setting, while at the same time, suboptimal query plans can be disastrous with large datasets. In this paper, we propose new techniques that take into account UDFs and correlations between relations for optimizing queries running on large scale clusters. We introduce "pilot runs", which execute part of the query over a sample of the data to estimate selectivities, and employ a cost-based optimizer that uses these selectivities to choose an initial query plan. Then, we follow a dynamic optimization approach, in which plans evolve as parts of the queries get executed. Our experimental results show that our techniques produce plans that are at least as good as, and up to 2x (4x) better for Jaql (Hive) than, the best hand-written left-deep query plans.

关键词： query optimization large-scale data platforms adaptive query processing pilot runs

来源：评论

学校读者我要写书评

暂无评论

GIRAFFE: A scalable distributed coordination service for large-scale systems 16

GIRAFFE: A scalable distributed coordination service for lar...

引用

16th IEEE International Conference on Cluster Computing, CLUSTER 2014

作者： Shi, Xuanhua Lin, Haohong Jin, Hai Zhou, Bing Bing Yin, Zuoning Di, Sheng Wu, Song Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Information Technologies University of Sydney Australia GraphSQL Inc. Australia INRIA Argonne National Laboratory United States

ISBN: (纸本)9781479955480

The scale of cloud services keeps increasing over time, significantly introducing huge challenges in system manageability and reliability. Designing coordination services in cloud is the right track to solve the above problems. However, existing coordination services (e.g., Chubby and ZooKeeper) only perform well in read-intensive scenario and small ensemble scales. To this end, we propose Giraffe, a scalable distributed coordination service. There are three important contributions in our design. (1) Giraffe organizes coordination servers using interior-node-disjoint trees for better scalability. (2) Giraffe employs a novel Paxos protocol for strong consistency and fault-tolerance. (3) Giraffe supports hierarchical data organization and in-memory storage for high throughput and low latency. We evaluate Giraffe on a high performance computing test-bed. The experimental results show that Giraffe gains much better write performance than ZooKeeper when server ensemble is large. Giraffe is nearly 300% faster than ZooKeeper on update operations when ensemble size is 50 servers. Experiments also show that Giraffe reacts and recovers more quickly than ZooKeeper against node failures. © 2014 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Workload-Driven Antijoin Cardinality Estimation

引用

ACM TRANSACTIONS ON DATABASE SYSTEMS 2015年第3期40卷 16-16页

作者： Rusu, Florin Zhuang, Zixuan Wu, Mingxi Jermaine, Chris Univ Calif Merced Sch Engn Merced CA 95343 USA GraphSQL Inc Mountain View CA 94043 USA Rice Univ Dept Comp Sci Houston TX 77005 USA

Antijoin cardinality estimation is among a handful of problems that has eluded accurate efficient solutions amenable to implementation in relational query optimizers. Given the widespread use of antijoin and subset-based queries in analytical workloads and the extensive research targeted at join cardinality estimation-a seemingly related problem-the lack of adequate solutions for antijoin cardinality estimation is intriguing. In this article, we introduce a novel sampling-based estimator for antijoin cardinality that (unlike existent estimators) provides sufficient accuracy and efficiency to be implemented in a query optimizer. The proposed estimator incorporates three novel ideas. First, we use prior workload information when learning a mixture superpopulation model of the data offline. Second, we design a Bayesian statistics framework that updates the superpopulation model according to the live queries, thus allowing the estimator to adapt dynamically to the online workload. Third, we develop an efficient algorithm for sampling from a hypergeometric distribution in order to generate Monte Carlo trials, without explicitly instantiating either the population or the sample. When put together, these ideas form the basis of an efficient antijoin cardinality estimator satisfying the strict requirements of a query optimizer, as shown by the extensive experimental results over synthetically-generated as well as massive TPC-H data.

关键词： Algorithms Design Experimentation Performance Antijoin operator query optimization sampling Monte Carlo Bayesian statistics

来源：评论

学校读者我要写书评

暂无评论

Jo-DPMF: Differentially private matrix factorization learning through joint optimization

引用

INFORMATION SCIENCES 2018年 467卷 271-281页

作者： Zhang, Feng Lee, Victor E. Choo, Kim-Kwang Raymond China Univ Geosci Sch Comp Sci Wuhan 430074 Hubei Peoples R China China Univ Geosci Hubei Key Lab Intelligent Geoinformat Proc Wuhan 430074 Hubei Peoples R China GraphSQL Inc Mountain View CA 94043 USA Univ Texas San Antonio Dept Informat Syst & Cyber Secur San Antonio TX 78249 USA Univ South Australia Informat Assurance Res Grp Adelaide SA 5095 Australia

Stochastic gradient descent (SGD) is a widely-used technique to implement matrix factorization. SGD-based matrix factorization involves many iterative computations. Therefore, according to the sequential composition theory of differential privacy, conventional implementation strategies of differentially private matrix factorization may lead to significant error accumulation, no matter whether the Laplace noise is added to the original matrix or to the factorized matrices. In fact, the implementation of differentially private matrix factorization is so challenging that results proposed to date have the problem of inefficient privacy and data utility. In this paper, we employ the objective perturbation method to address the challenge;this method dramatically alleviates error accumulation by perturbing the objective function instead of perturbing the results. Our method outperforms the state-of-the-art methods since it only requires a scalar noise rather than a vector noise to achieve the same magnitude of privacy. Furthermore, our method may learn the resulted matrices by joint optimization, which follows the conventional learning procedure of SGD and optimizes its convergence speed and accuracy as much as possible. In addition to the differential privacy guarantee, we also empirically show the way that the novel model works together with k-coRating, a k-anonymity-like privacy preserving model, to enhance data utility. (C) 2018 Elsevier inc. All rights reserved.

关键词： Matrix factorization Differential privacy Recommender systems Collaborative filtering Stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

Fast algorithms to evaluate collaborative filtering recommender systems

引用

KNOWLEDGE-BASED SYSTEMS 2016年 96卷 96-103页

作者： Zhang, Feng Gong, Ti Lee, Victor E. Zhao, Gansen Rong, Chunming Qu, Guangzhi China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China China Univ Geosci Hubei Key Lab Intelligent Geoinformat Proc Wuhan 430074 Peoples R China GraphSQL Inc Mountain View CA 94043 USA S China Normal Univ Sch Comp Sci Guangzhou 510631 Guangdong Peoples R China Univ Stavanger Fac Sci & Technol N-4036 Stavanger Norway Oakland Univ Dept Engn & Comp Sci Rochester MI 48309 USA

Before deploying a recommender system, its performance must be measured and understood. So evaluation is an integral part of the process to design and implement recommender systems. In collaborative filtering, there are many metrics for evaluating recommender systems. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are among the most important and representative ones. To calculate MAE/RMSE, predicted ratings are compared with their corresponding true ratings. To predict item ratings, similarities between active users and their candidate neighbors need to be calculated. The complexity for the traditional and naive similarity calculation corresponding to user u and user v is quadratic in the number of items rated by u and v. In this paper, we explore the mathematical regularities underlying the similarity formulas, introduce a novel data structure, and design linear time algorithms to calculate the similarities. Such complexity improvement shortens the evaluation time and will finally contribute to increasing the efficiency of design and development of recommender systems. Experimental results confirm the claim. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Recommender systems Collaborative filtering MAE/RMSE Evaluation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：