检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chen, Zhexue Huang, Hong Liu, Bang Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Huazhong University of Science and Technology China RALI & Mila University of Montreal

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment. Most existing research addresses this problem in a multi-stage pipeline manner, which neglects the mutual information between such three elements and has the problem of error propagation. In this paper, we propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model (S3E2) to fully exploit the syntactic and semantic relationships between the triplet elements and jointly extract them. Specifically, we design a Graph-Sequence duel representation and modeling paradigm for the task of ASTE: we represent the semantic and syntactic relationships between word pairs in a sentence by graph and encode it by Graph Neural Networks (GNNs), as well as modeling the original sentence by LSTM to preserve the sequential information. Under this setting, we further apply a more efficient inference strategy for the extraction of triplets. Extensive evaluations on four benchmark datasets show that S3E2 significantly outperforms existing approaches, which proves our S3E2’s superiority and flexibility in an end-to-end fashion. Copyright © 2021, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search

arXiv

引用

arXiv 2024年

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei Zhang, Xuecang Zhu, Junhua Zhang, Yu 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 China Huawei Technologies Co. Ltd China

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services None of modern ANNS systems can address these issues simultaneously. We present FusionANNS, a high-throughput, low-latency cost-efficient, and high-accuracy ANNS system for billion scale datasets using SSDs and only one entry-level GPU The key idea of FusionANNS lies in CPU/GPU collabo rative filtering and re-ranking mechanisms, which signifi cantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We imple ment FusionANNS and compare it with the state-of-the-art SSD-based ANNS system–SPANN and GPU-accelerated in memory ANNS system–RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN;2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Schema adaptive modeling and incremental matching for web interface

Schema adaptive modeling and incremental matching for web in...

引用

International Conference on Semantic computing

作者： Heng Chen Hai Jin Feng Zhao Lei Zhu Service Computing Technology and System Lab Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology Wuhan Hubei CN

ISBN: (纸本)9781479979363

There are so many web data hidden behind so-called deep web and can only be accessed through query interfaces, and the data volume is increasing. We often need to fill forms over alternative interfaces in the same domain to select the best product or service, such as buying a book across various online book websites to choose the most affordable one. Integrating these web interfaces in the same domain to an uniform interface is as a matter of course. One of the most important things for interface integration is interface schema matching. In this paper, we present a new structure and a corresponding algorithm for web interface schema modeling and matching. Using the new schema structure, we could not only easily handle two interfaces schema matching, but also handle incremental schema matching between an existing integrated interface and a new interface. We present a detailed experimental evaluation using UIUC Web Integration Repository dataset. The results show that our approach is effective: it obtains significantly higher accuracy for two schema matching and is more robust than previous techniques. For incremental schema matching, it also performs well.

关键词： Accuracy

来源：评论

学校读者我要写书评

暂无评论

Multi-task representation learning with multi-view graph convolutional networks

arXiv

引用

arXiv 2021年

作者： Huang, Hong Song, Yu Wu, Yao Shi, Jia Xie, Xia Jin, Hai National Engineering Research Center for Big Data Technology Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform these two tasks separately, which requires a lot of duplication of work and ignores the correlations between tasks. Besides, conventional models suffer from the identical treatment of information of multiple views, thus they fail to learn robust representation for downstream tasks. To this end, we tackle link prediction and node classification problems simultaneously via multi-task multi-view learning in this paper. We first explain the feasibility and advantages of multi-task multi-view learning for these two tasks. Then we propose a novel model named as MT-MVGCN to perform link prediction and node classification tasks simultaneously. More specifically, we design a multi-view graph convolutional network to extract abundant information of multiple views in a network, which is shared by different tasks. We further apply two attention mechanisms: view attention mechanism and task attention mechanism to make views and tasks adjust the view fusion process. Moreover, view reconstruction can be introduced as an auxiliary task to boost the performance of the proposed model. Experiments on real-world network datasets demonstrate that our model is efficient yet effective, and outperforms advanced baselines in these two tasks. © 2021, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

PRIVACY-PRESERVING CLOUD-BASED VIDEO SURVEILLANCE WITH ADJUSTABLE GRANULARITY OF PRIVACY PROTECTION

PRIVACY-PRESERVING CLOUD-BASED VIDEO SURVEILLANCE WITH ADJUS...

引用

IEEE International Conference on Image Processing

作者： Xiaojing Ma Huan Peng Hai Jin Bin Zhu Service Computing Technology and System Lab Huazhong University of Science and Technology Wuhan Hubei China Microsoft Research Asia Beijing China

Cloud-based video surveillance requires protecting privacy yet allowing cloud to perform motion detection and tracking. Prior art allows performing surveillance on encrypted videos but details of trajectories of moving objects are exposed. In this paper, we propose a video surveillance system that supports adjustable granularity of motion detection and tracking for fine-grained control on conflicting requirements between privacy protection and accuracy of motion detection and tracking. Our encryption adds a permutation layer to conventional format-compliant selective encryption to ensure motion information can be recovered only at a given granularity yet incurs a very small impact on the bitrate and processing speed of video compression. Our motion detection method estimates both local and global motions to distinguish foreground motions from background motions and deduce trajectories of foreground moving objects. Experimental results indicate that our system has fulfilled the design goal.

关键词： Trajectory Encryption Motion detection Tracking Video surveillance

来源：评论

学校读者我要写书评

暂无评论

A comprehensive QoS determination model for Infrastructure-as-a-service clouds

A comprehensive QoS determination model for Infrastructure-a...

引用

2013 IEEE International Conference on Automation Science and Engineering, CASE 2013

作者： Xia, Yunni Zhou, Mengchu Luo, Xin Zhu, Qingsheng Software Theory and Technology Chongqing Key Lab Chongqing University Chongqing 400030 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102 United States

ISBN: (纸本)9781479915156

Cloud computing is a recently developed new technology for complex systems with massive service sharing, which is different from the resource sharing of the grid computing systems. In a cloud environment, service requests from users go through numerous provider specific steps from the instant it is submitted to when the service is fully delivered. Quality modeling and analysis of clouds are not easy tasks because of the complexity of the provisioning mechanism and the dynamic cloud environment. This study proposes an analytical modelbased approach for quality evaluation of Infrastructure-as-a-service cloud and consider expected request completion time, rejection probability, and system overhead rate as key QoS metrics. It also features with the modeling of different warming and cooling strategies of machines and the ability to identify the optimal balance between system overhead and performance. © 2013 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Construct pairwise test suites based on the Bak-Sneppen model of biological evolution

引用

World Academy of Science, Engineering and technology 2009年 35卷 224-229页

作者： Yuan, Jianjun Jiang, Changjun Department of Computer Science and Technology The Key Lab. of 'Embedded System and Service Computing' Ministry of Education of China Tongji University Shanghai 201804 China

Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by unexpected 2-way interactions among system factors. Although meta-heuristic strategies like simulated annealing can generally discover smaller pairwise test suite, they may cost more time to perform search, compared with greedy algorithms. We propose a new method, improved Extremal Optimization (EO) based on the Bak-Sneppen (BS) model of biological evolution, for constructing pairwise test suites and define fitness function according to the requirement of improved EO. Experimental results show that improved EO gives similar size of resulting pairwise test suite and yields an 85% reduction in solution time over SA.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Superpage-Friendly Page Table Design for Hybrid Memory systems

Superpage-Friendly Page Table Design for Hybrid Memory Syste...

引用

2020国际计算机前沿大会

作者： Xiaoyuan Wang Haikun Liu Xiaofei Liao Hai Jin National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Service Computing Technology and System Lab Huazhong University of Science and Technology Cluster and Grid Computing Lab Huazhong University of Science and Technology School of Computer Science and Technology Huazhong University of Science and Technology

Page migration has long been adopted in hybrid memory systems comprising dynamic random access memory(DRAM) and non-volatile memories(NVMs), to improve the system performance and energy ***, page migration introduces some side effects, such as more translation lookaside buffer(TLB) misses, breaking memory contiguity, and extra memory accesses due to page table updating. In this paper, we propose superpagefriendly page table called SuperPT to reduce the performance overhead of serving TLB misses. By leveraging a virtual hashed page table and a hybrid DRAM allocator, SuperPT performs address translations in a flexible and efficient way while still remaining the contiguity within the migrated pages.

关键词： Pagetable Hybridmemorysystem Pagemigration Multiplepagesizes Addresstranslation

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery

arXiv

引用

arXiv 2023年

作者： Zhang, Xiao Zhang, Hai Zhou, Hongtu Huang, Chang Zhang, Di Ye, Chen Zhao, Junqiao The Department of Computer Science and Technology Tongji University China The MOE Key Lab of Embedded System and Service Computing Tongji University China

Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. To ensure safety during and after training process, existing methods tend to adopt overly conservative policy to avoid unsafe situations. However, overly conservative policy severely hinders the exploration, and makes the algorithms substantially less rewarding. In this paper, we propose a method to construct a boundary that discriminates safe and unsafe states. The boundary we construct is equivalent to distinguishing dead-end states, indicating the maximum extent to which safe exploration is guaranteed, and thus has minimum limitation on exploration. Similar to Recovery Reinforcement Learning, we utilize a decoupled RL framework to learn two policies, (1) a task policy that only considers improving the task performance, and (2) a recovery policy that maximizes safety. The recovery policy and a corresponding safety critic are pretrained on an offline dataset, in which the safety critic evaluates upper bound of safety in each state as awareness of environmental safety for the agent. During online training, a behavior correction mechanism is adopted, ensuring the agent to interact with the environment using safe actions only. Finally, experiments of continuous control tasks demonstrate that our approach has better task performance with less safety violations than state-of-the-art algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-time action recognition with enhanced motion vector CNNs

Real-time action recognition with enhanced motion vector CNN...

引用

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

作者： Zhang, Bowen Wang, Limin Wang, Zhe Qiao, Yu Wang, Hanli Shenzhen Key Lab of Comp. Vis. and Pat. Rec. Shenzhen Institutes of Advanced Technology CAS China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Computer Vision Lab ETH Zurich Switzerland

ISBN: (纸本)9781467388511

The deep two-stream architecture [23] exhibited excellent performance on video based action recognition. The most computationally expensive step in this approach comes from the calculation of optical flow which prevents it to be real-time. This paper accelerates this architecture by replacing optical flow with motion vector which can be obtained directly from compressed videos without extra calculation. However, motion vector lacks fine structures, and contains noisy and inaccurate motion patterns, leading to the evident degradation of recognition performance. Our key insight for relieving this problem is that optical flow and motion vector are inherent correlated. Transferring the knowledge learned with optical flow CNN to motion vector CNN can significantly boost the performance of the latter. Specifically, we introduce three strategies for this, initialization transfer, supervision transfer and their combination. Experimental results show that our method achieves comparable recognition performance to the state-of-the-art, while our method can process 390.7 frames per second, which is 27 times faster than the original two-stream method.

关键词： Pattern recognition

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：