检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Hao Wu Junxiao Deng Hao Fan Shadi Ibrahim Song Wu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Inria Univ. Rennes CNRS IRISA France

Machine Learning (ML) workflows are increasingly deployed on serverless computing platforms to benefit from their elasticity and fine-grain pricing. Proper resource allocation is crucial to achieve fast and cost-efficient execution of serverless ML workflows (specially for hyperparameter tuning and model training). Unfortunately, existing resource allocation methods are static, treat functions equally, and rely on offline prediction, which limit their efficiency. In this paper, we introduce CE-scaling – a Cost-Efficient autoscaling framework for serverless ML work-flows. During the hyperparameter tuning, CE-scaling partitions resources across stages according to their exact usage to minimize resource waste. Moreover, it incorporates an online prediction method to dynamically adjust resources during model training. We implement and evaluate CE-scaling on AWS Lambda using various ML models. Evaluation results show that compared to state-of-the-art static resource allocation methods, CE-scaling can reduce the job completion time and the monetary cost by up to 63% and 41% for hyperparameter tuning, respectively; and by up to 58% and 38% for model training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach

arXiv

引用

arXiv 2024年

作者： Wan, Yao Wan, Guanghua Zhang, Shijie Zhang, Hongyu Zhou, Pan Jin, Hai Sun, Lichao National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology China University of Leigh United States

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Examples of such models include CodeGPT and StarCoder. These models are typically trained from a large amount of source code collected from open-source communities such as GitHub. Although using source code in GitHub has been a common practice for training deep-learning-based models for code completion, it may induce some legal and ethical issues such as copyright infringement. In this paper, we investigate the legal and ethical issues of current neural code completion models by answering the following question: Is my code used to train your neural code completion model? To this end, we tailor a membership inference approach (termed CodeMI) that was originally crafted for classification tasks to a more challenging task of code completion. In particular, since the target code completion models perform as opaque black boxes, preventing access to their training data and parameters, we opt to train multiple shadow models to mimic their behavior. The acquired posteriors from these shadow models are subsequently employed to train a membership classifier. Subsequently, the membership classifier can be effectively employed to deduce the membership status of a given code sample based on the output of a target code completion model. We comprehensively evaluate the effectiveness of this adapted approach across a diverse array of neural code completion models, (i.e., LSTM-based, CodeGPT, CodeGen, and StarCoder). Experimental results reveal that the LSTM-based and CodeGPT models suffer the membership leakage issue, which can be easily detected by our proposed membership inference approach with an accuracy of 0.842, and 0.730, respectively. Interestingly, our experiments also show that the data membership of current large language models of code, e.g., CodeGen and StarCoder, is difficult to detect, leaving amper space for further improvement. Finally, we also t

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Information Value Evaluation Model for ILM

Information Value Evaluation Model for ILM

引用

ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed computing (SNPD)

作者： Hai Jin Muzhou Xiong Song Wu Services Computing Technology and System Lab Huazhong University of Science and Technology Wuhan China Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769532639

The first step towards the information lifecycle management is to differentiate information by values. This paper presents an evaluation model for information value. The idea of the model is from commodity value discipline in economic area. The output of information value evaluation model is determined by information itself which is like commodity price is determined by use-value in economic area. The output of the model is changed around the real information value and controlled by the relationship between information supply and demand. The output of the model is determined by factors from three aspects that are information itself, information supply, and information demand. When applying the model into traditional information management approaches, such as replication, data migration, and backup, those mechanisms control the output of the model through adjusting the ability of information supply.

关键词： Biological system modeling Supply and demand Computational modeling Bandwidth Data models Economics Analytical models

来源：评论

学校读者我要写书评

暂无评论

Scalable Hash Ripple Join on Spark

Scalable Hash Ripple Join on Spark

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Hao Liu Jiang Xiao Fengchao Peng The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Services Computing Technology and System Lab Cluster and Grid Computing Lab Shool of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (纸本)9781538632086

Hash Ripple join is an online aggregation algorithm that can rapidly give good approximate join results increases with the progress of the join operation and converges to the real result when the join finishes. Luo et al. proposed a parallel hash ripple join (PHRJ) that runs in a distributed setting. However, the PHRJ has two drawbacks when handling large-scale data: 1) PHRJ updates approximate results in fine grain which induces extra communication cost in a distributed environment 2) When data is out of memory, PHRJ cannot provide unbiased approximate result. In this thesis, a scalable hash ripple join is proposed that 1) runs on a distributed framework that can process distributed data in coarse-grain to speed up the join performance; 2) continuously gives unbiased and consistent approximate join results even in the presence of memory overflow; and 3) has good scalability handling growing amount of data. We have implemented a prototype of the scalable hash ripple join (SHRJ) algorithm on Spark. Experiment results show that SHRJ can give good approximate join result while taking less than 10% of the time of Spark's own join operator.

关键词： Sparks Distributed databases Approximation algorithms clustering algorithms Indexes Standards Computer science

来源：评论

学校读者我要写书评

暂无评论

A Hierachical VoIP system Based on Peer-to-Peer SIP: A Manageable Approach

A Hierachical VoIP System Based on Peer-to-Peer SIP: A Manag...

引用

International Conference on Computer and Information technology (CIT)

作者： Linchen Yu Xiaofei Liao Hai Jin Pengcheng Qin Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computer China University of Geoscience Wuhan China

Peer-to-Peer SIP is proposed to leverage Peer-to-Peer computing to control multimedia sessions in a decentralized manner. A lot of companies can be benefited if conventional SIP environment does not require the configuration and maintenance of central servers. However, existing P2PSIP systems put too much emphasis on the decentralization of SIP elements and the briefness of distribution. To some extent, P2PSIP system is manageable, but the control of the entire system is still relatively weak. In this paper, we propose a hierarchical P2PSIP system to address the manageable problems. Actual deployment and exhaustive simulations are performed to evaluate the performance of our P2PSIP schemes. Results indicate that the manageable approach not only solves the control liability problem, but also performs good reliability, scalability, and interoperability.

关键词： Servers Tin Reliability Protocols IP networks Authentication Registers

来源：评论

学校读者我要写书评

暂无评论

AFaVS: Accurate Yet Fast Version Switching for Graph Processing systems

AFaVS: Accurate Yet Fast Version Switching for Graph Process...

引用

International Conference on Data Engineering

作者： Long Zheng Xiangyu Ye Haifeng Liu Qinggang Wang Yu Huang Chuangyi Gui Pengcheng Yao Xiaofei Liao Hai Jin Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China School of Computer Science and Engineering UNSW Sydney Australia

Multi-version graph processing has been widely used to solve many real-world problems. The process of the multi-version graph processing typically includes: (1) a history graph version switching at a specific time and (2) graph processing on this history graph. Existing multi-version graph systems assume ideally that every request for a particular graph version at a particular time will have a corresponding snapshot available. However, in most cases, this is not true. Then existing solutions usually have to settle with an "approximating" version as a substitute, leading to unexpected results for the underlying graph algorithm and thus reducing the practicality of a multi-version graph system for many application scenarios *** this paper, we observe that only a few graph updates have a great impact on the final results. We therefore present AFaVS, a novel multi-version graph system that can improve accuracy effectively in both time- and memory-efficient manners. The cornerstone of AFaVS lies in a novel concept "value" that characterizes the importance of graph updates. AFaVS proposes differential management of updates based on their values and achieves higher accuracy while preserving processing and memory efficiency. AFaVS is also equipped with value-guided version switching and locality-aware optimizations to boost its overall efficiency. Our results on a variety of real-world datasets show that AFaVS outperforms four state-of-the-art multi-version graph systems by 74.35%~95.72% in terms of accuracy improvement and 57.03%~90.44% in terms of memory reduction while introducing less than 2.96% extra computing time. We have deployed AFaVS in a disaster recovery system on the production cluster of Alibaba, achieving 78.8%~90.1% fewer error rates than advanced systems at a comparable efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Pipelined GCN with Communication-Efficient Sampling and Inclusion-Aware Caching

On Pipelined GCN with Communication-Efficient Sampling and I...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Shulin Wang Qiang Yu Xiong Wang Yuqing Li Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Graph convolutional network (GCN) has achieved enormous success in learning structural information from unstructured data. As graphs become increasingly large, distributed training for GCNs is severely prolonged by frequent cross-worker communications. Existing efforts to improve the training efficiency often come at the expense of GCN performance, while the communication overhead persists. In this paper, we propose PSC-GCN, a holistic pipelined framework for distributed GCN training with communication-efficient sampling and inclusion-aware caching, to address the communication bottleneck while ensuring satisfactory model performance. Specifically, we devise an asynchronous pre-fetching scheme to retrieve stale statistics (features, embedding, gradient) of boundary nodes in advance, such that the embedding aggregation and model update are pipelined with statistics transmission. To alleviate communication volume and staleness effect, we introduce a variance-reduction based sampling policy, which prioritizes inner nodes over boundary ones for reducing the access frequency to remote neighbors, thus mitigating cross-worker statistics exchange. Complementing graph sampling, a feature caching module is co-designed to buffer hot nodes with high inclusion probability, ensuring that frequently sampled nodes will be available in local memory. Extensive evaluations on real-world datasets show the superiority of PSC-GCN over state-of-the-art methods, where we can reduce training time by 72%-80% without sacrificing model accuracy.

关键词： Training Estimation error Accuracy Graph convolutional networks Computational modeling Probability Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

LaLDPC: Latency-aware LDPC for read performance improvement of solid state drives 33

LaLDPC: Latency-aware LDPC for read performance improvement ...

引用

33rd International Conference on Massive Storage systems and technology, MSST 2017

作者： Du, Yajuan Zou, Deqing Li, Qiao Shi, Liang Jin, Hai Xuey, Chun Jason Service Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Technol. and Syst. Lab Sch. of Comp. Sci. and Technology Huazhong Univ. of Sci. and Technol. Wuhan430074 China Department of Computer Science City University of Hong Kong Kowloon Hong Kong College of Computer Science Chongqing University Chongqing China

High-density Solid State Drives (SSDs) have to use Low-Density Parity-Check (LDPC) codes to store data reliably. Current LDPC implementations apply multiple read-retry steps to find the appropriate set of multiple Reference Voltage (RVs) for successful decoding. These appropriate RVs, number of which is represented by read level, cannot be obtained in advance, instead, an iterative read-retry LDPC process happens that starts with the first read level with the smallest number of RVs and then increases the level until that the data have been successfully decoded. Only read-retry with the last read level, called the appropriate read level, is necessary. Read latency can be improved by avoiding read-retries. This becomes particularly important in the late stage of SSD life when high read levels are needed. To avoid unnecessary read-retries, this paper proposes Latency-aware LDPC (LaLDPC). We study read level characteristics along with data retention and observe that a single read level stays appropriate for a long time. During this time, all reads in the same page have probably the same appropriate read level, which we call the temporal read level locality. Using this value, LaLDPC estimates the starting read voltage level, which we store in the flash translation layer of the controller. As an example, we show how to integrate LaLDPC into the Demand-based Flash Translation Layer (DFTL). A new cache eviction algorithm is also proposed to leave entries with high read levels in the cache as long as possible. Experimental results show that LaLDPC saves 56% of read retries and improves SSD read performance by 18% on average compared with the existing LDPC method. © 33rd International Conference on Massive Storage systems and technology, MSST 2017. All rights reserved.

关键词： Forward error correction

来源：评论

学校读者我要写书评

暂无评论

SumPA: Efficient Pattern-Centric Graph Mining with Pattern Abstraction 21

SumPA: Efficient Pattern-Centric Graph Mining with Pattern A...

引用

Proceedings of the 30th International Conference on Parallel Architectures and Compilation Techniques

作者： Chuangyi Gui Xiaofei Liao Long Zheng Pengcheng Yao Qinggang Wang Hai Jin National Engineering Research Center for Big Data Technology and System/Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665442787

Graph mining aims to explore interesting structural information of a graph. Pattern-centric systems typically transform a generic-purpose graph mining problem into a series of subgraph matching problems for high performance. Existing pattern-centric mining systems reduce the substantial search space towards a single pattern by exploring a highly-optimized matching order, but inherent computational redundancies of such a matching order itself still suffer severely, leading to significant performance degradation. The key innovation of this work lies in a general redundancy criterion that characterizes computational redundancies arising in not only handing a single pattern but also matching multiple patterns simultaneously. In this paper, we present SumPA, a high-performance pattern-centric graph mining system that can sufficiently remove redundant computations for any complex graph mining problems. SumPA features three key designs: (1) a pattern abstraction technique that can simplify numerous complex patterns into a few simple abstract patterns based on pattern similarity, (2) abstraction-guided pattern matching that completely eliminates (totally and partially) redundant computations during subgraph enumeration, and (3) a suite of system optimizations to maximize storage and computation efficiency. Our evaluation on a wide variety of real-world graphs shows that SumPA outperforms the two state-of-the-art systems Peregrine and GraphPi by up to 61.89× and 8.94×, respectively. For many mining problems on large graphs, Peregrine takes hours or even days while SumPA finishes in only a few minutes.

关键词： data reuse

来源：评论

学校读者我要写书评

暂无评论

ACGraph: Accelerating Streaming Graph Processing via Dependence Hierarchy

ACGraph: Accelerating Streaming Graph Processing via Depende...

引用

Design Automation Conference

作者： Zihan Jiang Fubing Mao Yapu Guo Xu Liu Haikun Liu Xiaofei Liao Hai Jin Wei Zhang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electronic and Computer Engineering HKUST Hong Kong

Streaming graph processing needs to timely evaluate continuous queries. Prior systems suffer from massive redundant computations due to the irregular order of processing vertices influenced by updates. To address this issue, we propose ACGraph, a novel streaming graph processing approach for monotonic graph algorithms. It maintains dependence trees during runtime, and makes affected vertices processed in a top-to-bottom order in the hierarchy of the dependence trees, thus normalizing the state propagation order and coalescing of multiple propagation to the same vertices. Experimental results show that ACGraph reduces the number of updates by 50% on average, and achieves the speedup of 1.75~7.43× over state-of-the-art systems.

关键词：

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：