检索结果-内蒙古大学图书馆

BGAE: Auto-Encoding Multi-View Bipartite Graph Clustering

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第8期36卷 3682-3696页

作者： Li, Liang Pan, Yuangang Liu, Jie Liu, Yue Liu, Xinwang Li, Kenli Tsang, Ivor W. Li, Keqin Natl Univ Def Technol Sch Comp Changsha 410073 Peoples R China ASTAR Ctr Frontier AI Res Singapore 138632 Singapore Natl Univ Def Technol Sci & Technol & Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410073 Peoples R China Hunan Univ Supercomp & Cloud Comp Inst Changsha 410073 Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY 12561 USA

Unsupervised multi-view bipartite graph clustering (MVBGC) is a fast-growing research, due to promising scalability in large-scale tasks. Although many variants are proposed by various strategies, a common design is to construct the bipartite graph directly from the input data, i.e., only consider the unidirectional "encoding" process. However, "encoding-decoding" mechanism is a popular design for deep learning, the most representative one is auto-encoder (AE). Enlightened by this, this paper rethinks existing MVBGC paradigms and transfers the "encoding-decoding" design into graph machine learning, and proposes a novel framework termed auto-encoding multi-view bipartite graph clustering (BGAE), which integrates encoding, bipartite graph construction, and decoding modules in a self-supervised learning manner. The encoding module extracts a latent joint representation from the input data, the bipartite graph construction module learns a bipartite graph with connectivity constraint in latent semantic space, and the decoding module recreates the input data via the bipartite graph. Therefore, our novel BGAE combines representation learning, bipartite graph learning, reconstruction learning, and label inference into a unified framework. All the modules are seamlessly integrated and mutually reinforcing for clustering-friendly purposes. Extensive experiments verify the superiority of our novel design and the significance of "decoding" process. To the best of our knowledge, this is the first attempt to explore "encoding-decoding" design in traditional MVBGC.

关键词： Bipartite graph Decoding Machine learning Encoding Synthetic data Matrix decomposition Image reconstruction Bipartite graph learning encoding-decoding graph machine learning multi-view clustering

来源：评论

学校读者我要写书评

暂无评论

FCloudless: A Performance-Aware Collaborative Mechanism for JointCloud Serverless 14

FCloudless: A Performance-Aware Collaborative Mechanism for ...

引用

IEEE 14th International Conference on Joint Cloud Computing (JCC)

作者： Liu, Jianfei Wang, Huaimin Shi, Peichang Li, Yaojie Ma, Penghui Yi, Guodong Natl Univ Def Technol Coll Comp Sci Natl Key Lab Parallel & Distributed Comp Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Sci Key Lab Software Engn Complex Syst Changsha 410073 Peoples R China Xiangjiang Lab Changsha 410073 Peoples R China Hunan Univ Technol & Business Sch Adv Interdisciplinary Studies Changsha 410073 Peoples R China

ISBN: (纸本)9798350328554

As a new stage in the development of the cloud computing paradigm, serverless computing has the high-level abstraction characteristic of shielding underlying details. This makes it extremely challenging for users to choose a suitable serverless platform. To address this, targeting the jointcloud computing scenario of heterogeneous serverless platforms across multiple clouds, this paper presents a jointcloud collaborative mechanism called FCloudless with cross-cloud detection of the full lifecycle performance of serverless platforms. Based on the benchmark metrics set that probe performance critical stages of the full lifecycle, this paper proposes a performance optimization algorithm based on detected performance data that takes into account all key stages that affect the performance during the lifecycle of a function and predicts the overall performance by combining the scores of local stages and dynamic weights. We evaluate FCloudless on AWS, AliYun, and Azure. The experimental results show that FCloudless can detect the underlying performance of serverless platforms hidden in the black box and its optimization algorithm can select the optimal scheduling strategy for various applications in a jointcloud environment. FCloudless reduces the runtime by 23.3% and 24.7% for cold and warm invocations respectively under cost constraints.

关键词： serverless JointCloud benchmarking performance optimization

来源：评论

学校读者我要写书评

暂无评论

FSS: A Flexible Scaling Scheme for Blockchain Based on Stale Block Rate 13

FSS: A Flexible Scaling Scheme for Blockchain Based on Stale...

引用

13th IEEE International Conference on Joint Cloud Computing (JCC)

作者： Chen, Ming Shi, Peichang Fu, Xiang Jiang, Feng Gao, Fei Ma, Penghui Kong, Jinzhu Natl Univ Def Technol Coll Comp Sci Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Sci Key Lab Software Engn Complex Syst Changsha 410073 Peoples R China Kylin Software Co Ltd Changsha 410073 Peoples R China Zhejiang Lab Hangzhou 311100 Peoples R China

ISBN: (数字)9781665462853

ISBN: (纸本)9781665462853

In blockchain, there has long been a contradiction between the limited ability and the uncertain requirements of processing transactions, which seriously restricts the practical application of blockchain. Therefore, how to improve the scalability of blockchain has become an urgent issue to be solved. Some existing works have achieved blockchain expansion through increasing the upper limit of block size permanently, which makes the trade-off of the "Mundellian Trilemma" in blockchain (i.e. a blockchain system cannot be optimal in all the three dimensions of scalability, security and decentralization at the same time) fixed and thus not adapted to the dynamic environment. In this paper, we propose FSS, a flexible scaling scheme for blockchain based on stale block rate, which dynamically adjusts the upper limit of block size according to the stale block rate, not only expanding the blockchain when allowed, but also shrinking it when necessary. Experimental results indicate that FSS can reasonably improve the scalability of blockchain with required stale block rate.

关键词： blockchain scalability stale block rate

来源：评论

学校读者我要写书评

暂无评论

PPSS: A Privacy-Preserving Supervision Scheme Based on Blockchain 20

PPSS: A Privacy-Preserving Supervision Scheme Based on Block...

引用

20th IEEE Int Symposium on parallel and distributed Processing with Applicat / 15th IEEE Int Conf on Social Comp and Networking / 12th IEEE Int Conf on Big Data and Cloud Comp / 12th IEEE Int Conf on Sustainable Comp and Commun

作者： Chen, Ming Shi, Peichang Fu, Xiang Jiang, Feng Gao, Fei Ma, Penghui Kong, Jinzhu Natl Univ Def Mchnol Coll Comp Sci Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Sci Key Lab Software Engn Complex Syst Changsha 410073 Peoples R China Kylin Software Co LTD Changsha 410073 Peoples R China Zhejiang Lab Hangzhou 311100 Peoples R China

ISBN: (纸本)9781665464970

In JointCloud Computing, multi-party participation introduces complexity and uncertainty. For all participants in JointCloud Computing, both continuous supervision and necessary privacy protection are required. Traditional supervision methods usually adopt the centralized information interaction mode, which has such defects as collusion of interests, single point of failure, privacy disclosure, etc. Building a decentralized supervision mechanism has become a new research direction. In this paper, we propose PPSS, a privacy-preserving supervision scheme based on blockchain, which decentralizes the supervision of the participants in JointCloud Computing, and combines the "double encryptions" and "threshold encryption" technologies to provide privacy protection. While making full use of the decentralization of the blockchain, a committee is established to carry out the analysis and decision-making tasks in terms of supervision and privacy protection. Experimental results indicate that PPSS can balance performance and security by reasonably configuring the committee.

关键词： blockchain privacy-preserving supervision

来源：评论

学校读者我要写书评

暂无评论

EPP-MVSNet: Epipolar-assembling based Depth Prediction for Multi-view Stereo 18

EPP-MVSNet: Epipolar-assembling based Depth Prediction for M...

引用

18th IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Ma, Xinjun Gong, Yue Wang, Qirui Huang, Jingwei Chen, Lei Yu, Fan Huawei Technol Distributed & Parallel Software Lab Shenzhen Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

ISBN: (纸本)9781665428125

In this paper, we proposed EPP-MVSNet, a novel deep learning network for 3D reconstruction from multi-view stereo (MVS). EPP-MVSNet can accurately aggregate features at high resolution to a limited cost volume with an optimal depth range, thus, leads to effective and efficient 3D construction. Distinct from existing works which measure feature cost at discrete positions which affects the 3D reconstruction accuracy, EPP-MVSNet introduces an epipolar-assembling-based kernel that operates on adaptive intervals along epipolar lines for making full use of the image resolution. Further, we introduce an entropy-based refining strategy where the cost volume describes the space geometry with the little redundancy. Moreover, we design a light-weighted network with Pseudo-3D convolutions integrated to achieve high accuracy and efficiency. We have conducted extensive experiments on challenging datasets Tanks & Temples(TNT), ETH3D and DTU. As a result, we achieve promising results on all datasets and the highest F-Score on the online TNT intermediate benchmark. Code is available at https: //***/mindspore/mindspore/tree/master/model_zoo/research/cv/eppmvsnet.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

MRASS: Dynamic Task Scheduling enabled High Multi-cluster Resource Availability in JointCloud 13

MRASS: Dynamic Task Scheduling enabled High Multi-cluster Re...

引用

13th IEEE International Conference on Joint Cloud Computing (JCC)

作者： Gao, Fei Wang, Huaimin Shi, Peichang Fu, Xiang Zhong, Tao Kong, Jinzhu Natl Univ Def Technol Nat Key Lab Parallel & Distributed Proc Coll Comp Sci Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Sci Key Lab Software Engn Complex Syst Changsha 410073 Peoples R China Kylin Software Co Ltd Changsha 410073 Peoples R China Zhejiang Lab Hangzhou 311100 Peoples R China

ISBN: (数字)9781665462853

ISBN: (纸本)9781665462853

As the new paradigm of JointCloud Computing matures, enterprises are trying to build multiple Kubernetes clusters on different clouds to deploy tasks, with the advantages of disaster backup, low latency, and avoidance of single vendor lock-in, etc. Tasks in a JointCloud environment, always have highly diversified resource demands on CPU, memory, disk, and network. However, the mismatch between these tasks and heterogeneous clusters can easily cause many resource fragments, resulting in low resource availability. Therefore, the task scheduling strategy is the key to solving the above problem. The existing task schedule strategies for multi-clusters are always aiming at clusters' load balancing instead of increasing the resource availability. In this paper, we propose a dynamic task scheduling framework with the design of multi-cluster resource high-availability schedule strategy (MRASS) based on historical task resource consumption. MRASS conducts a cooperation model between multiple clusters and tasks, and proposes an indicator of resource availability, which is used to optimize the proportion of remaining resources of the cluster to keep approaching the proportion of resource requirements of future tasks, thereby execute more tasks within limited resources. Extensive numerical results confirm that the strategy has stable performance and performs well with different initial cluster resource setting, task resource type and task number. Compared with the existing algorithm, MRASS can place up to 20% more tasks, and the success rate of first placement of tasks can reach over 98%.

关键词： JointCloud multi-resource availability resource fragments multi-cluster cooperation

来源：评论

学校读者我要写书评

暂无评论

A scalable parallel preconditioned conjugate gradient method for bundle adjustment

引用

APPLIED INTELLIGENCE 2022年第1期52卷 753-765页

作者： Peng, Jiaxin Liu, Jie Wei, Hua Natl Univ Def Technol Sch Comp Sci Lab Software Engn Complex Syst Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Sch Comp Sci Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Hubei Univ Sci & Technol Sch Resources Environm Sci & Engn Water & Land Resources Res Ctr Middle Reaches Yan Xianning 437100 Hubei Peoples R China

Bundle adjustment is a fundamental problem in computer vision, with important applications such as 3D structure reconstruction from 2D images. This paper focuses on large-scale bundle adjustment tasks, e.g., city-wide 3D reconstruction, which require highly efficient solutions. For this purpose, it is common to apply the Levenberg-Marquardt algorithm, whose bottleneck lies in solving normal equations. The majority of recent methods focus on achieving scalability through modern hardware such as GPUs and distributed systems. On the other hand, the core of the solution, i.e., the math underlying the optimizer for the normal equations, remains largely unimproved since the proposal of the classic parallel bundle adjustment (PBA) algorithm, which increasingly becomes a major limiting factor for the scalability of bundle adjustment. This paper proposes parallel preconditioned conjugate gradient (PPCG) method, a novel parallel method for bundle adjustment based on preconditioned conjugate gradient, which achieves significantly higher efficiency and scalability than existing methods on the algorithmic level. The main idea is to exploit the sparsity of the Hessian matrix and reduce its structure parameters through an effective parallel Schur complement method;the result of this step is then fed into our carefully designed PPCG method which reduces matrix operations that are either expensive (e.g., large matrix reverse or multiplications) or scales poorly to multi-processors (e.g., parallel Reduce operators). Extensive experiments demonstrate that PPCG outperforms existing optimizers by large margins, on a wide range of datasets.

关键词： Structure from motion Bundle adjustment Preconditioned conjugate gradient

来源：评论

学校读者我要写书评

暂无评论

Transductive Relation-Propagation With Decoupling Training for Few-Shot Learning

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第11期33卷 6652-6664页

作者： Ma, Yuqing Bai, Shihao Liu, Wei Wang, Shuo Yu, Yue Bai, Xiao Liu, Xianglong Wang, Meng Beihang Univ State Key Lab Software Dev Environm Beijing 100191 Peoples R China Natl Univ Def Technol Coll Comp Key Lab Parallel & Distributed Comp Changsha 410073 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data Based Precis Med Beijing 100191 Peoples R China Hefei Univ Technol Sch Comp & Informat Sci Hefei 230009 Peoples R China

Few-shot learning, aiming to learn novel concepts from one or a few labeled examples, is an interesting and very challenging problem with many practical advantages. Existing few-shot methods usually utilize data of the same classes to train the feature embedding module and in a row, which is unable to learn adapting to new tasks. Besides, traditional few-shot models fail to take advantage of the valuable relations of the support-query pairs, leading to performance degradation. In this article, we propose a transductive relation-propagation graph neural network (GNN) with a decoupling training strategy (TRPN-D) to explicitly model and propagate such relations across support-query pairs, and empower the few-shot module the ability of transferring past knowledge to new tasks via the decoupling training. Our few-shot module, namely TRPN, treats the relation of each support-query pair as a graph node, named relational node, and resorts to the known relations between support samples, including both intraclass commonality and interclass uniqueness. Through relation propagation, the model could generate the discriminative relation embeddings for support-query pairs. To the best of our knowledge, this is the first work that decouples the training of the embedding network and the few-shot graph module with different tasks, which might offer a new way to solve the few-shot learning problem. Extensive experiments conducted on several benchmark datasets demonstrate that our method can significantly outperform a variety of state-of-the-art few-shot learning methods.

关键词： Task analysis Training Knowledge engineering Semantics Learning systems laboratories Extraterrestrial measurements Decoupling training few-shot learning knowledge transfer relation-propagation graph

来源：评论

学校读者我要写书评

暂无评论

Plumber: Boosting the Propagation of Vulnerability Fixes in the npm Ecosystem

引用

IEEE TRANSACTIONS ON software ENGINEERING 2023年第5期49卷 3155-3181页

作者： Wang, Ying Sun, Peng Pei, Lin Yu, Yue Xu, Chang Cheung, Shing-Chi Yu, Hai Zhu, Zhiliang Northeasthern Univ Software Coll Boston MA 02115 USA Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210093 Jiangsu Peoples R China Northeasthern Univ Software Coll Shenyang 110819 Peoples R China Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Peoples R China Nanjing Univ Dept Comp Sci & Technol State Key Lab Novel Software Technol Nanjing 210093 Jiangsu Peoples R China Hong Kong Univ Sci & Technol Guangzhou HKUST Fok Ying Tung Res Inst Guangzhou 511458 Peoples R China Northeastern Univ Natl Frontiers Sci Ctr Ind Intelligence & Syst Opt Key Lab Data Analyt & Optimizat Smart Ind Shenyang 110819 Peoples R China Northeastern Univ Software Coll Shenyang 110819 Peoples R China

Vulnerabilities are known reported security threats that affect a large amount of packages in the npm ecosystem. To mitigate these security threats, the open-source community strongly suggests vulnerable packages to timely publish vulnerability fixes and recommends affected packages to update their dependencies. However, there are still serious lags in the propagation of vulnerability fixes in the ecosystem. In our preliminary study on the latest versions of 356,283 active npm packages, we found that 20.0% of them can still introduce vulnerabilities via direct or transitive dependencies although the involved vulnerable packages have already published fix versions for over a year. Prior study by (Chinthanet et al. 2021) lays the groundwork for research on how to mitigate propagation lags of vulnerability fixes in an ecosystem. They conducted an empirical investigation to identify lags that might occur between the vulnerable package release and its fixing release. They found that factors such as the branch upon which a fix landed and the severity of the vulnerability had a small effect on its propagation trajectory throughout the ecosystem. To ensure quick adoption and propagation of a release that contains the fix, they gave several actionable advice to developers and researchers. However, it is still an open question how to design an effective technique to accelerate the propagation of vulnerability fixes. Motivated by this problem, in this paper, we conducted an empirical study to learn the scale of packages that block the propagation of vulnerability fixes in the ecosystem and investigate their evolution characteristics. Furthermore, we distilled the remediation strategies that have better effects on mitigating the fix propagation lags. Leveraging our empirical findings, we propose an ecosystem-level technique, Plumber, for deriving feasible remediation strategies to boost the propagation of vulnerability fixes. To precisely diagnose the causes of fix propagation

关键词： Empirical study npm ecosystem vulnerable dependencies

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multi-view Inter-passage Interactions for Neural Document Ranking 22

Leveraging Multi-view Inter-passage Interactions for Neural ...

引用

15th ACM International Conference on Web Search and Data Mining (WSDM)

作者： Fu, Chengzhen Hu, Enrui Feng, Letian Dou, Zhicheng Jia, Yantao Chen, Lei Yu, Fan Cao, Zhao Huawei Technol Co Ltd Distributed & Parallel Software Lab Shenzhen Peoples R China Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

ISBN: (纸本)9781450391320

The configuration of 512 window size prevents transformers from being directly applicable to document ranking that requires larger context. Hence, recent works propose to estimate document relevance with fine-grained passage-level relevance signals. A limitation of such models, however, is that scoring each passage independently falls short in modeling inter-passage interactions and leads to unsatisfactory results. In this paper, we propose a Multiview inter-passage Interaction based Ranking model (MIR), to combine intra-passage interactions and inter-passage interactions in a complementary manner. The former captures local semantic relations inside each passage, whereas the latter draws global dependencies between different passages. Moreover, we represent inter-passage relationships via multi-view attention patterns, allowing information propagation at token, sentence, and passage-level. The representations at different levels of granularity, being aware of global context, are then aggregated into a document-level representation for ranking. Experimental results on two benchmarks show that modeling inter-passage interactions brings substantial improvements over existing passage-level methods.

关键词： Document ranking Inter-passage attention Intra-passage attention

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：