检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Fang, Jinsheng Tao, Yuhao Zhu, Gupei School of Computer Science and Engineering Minnan Normal University Zhangzhou China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou China

Deep convolution network have been widely adopted in saliency detection in recent years and achieved state-of-the-art performance. A central issue for previous methods is the limited capability of detecting objects that are overwhelmed by complex background. Aim to address this problem, we propose a novel attention-based boundary-aware pyramid pooling network, namely ABAPNet, which consists of feature aggregation module, pyramid pooling module and cascading dual attention module. The proposed ABAPNet method transits high-level information to shallow layers to keep transferring important features between layers and obtains more semantic features. Hybrid loss by fusing binary cross entropy (BCE), structural similarity (SSIM) and intersection-over-union (IOU) is employed to reduce the gradient of mixed loss of network output features, which guides the network to better segment boundaries from complex background. Experimental results on 5 public datasets show that the proposed ABAPNet outperforms the competitors. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

3DS: An Efficient DPDK-based data Distribution Service for Distributed Real-time Applications

3DS: An Efficient DPDK-based Data Distribution Service for D...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Tianyu Xu Xianzhang Chen Changze Wu Jiapin Wang Rongwei Zheng Duo Liu Yujuan Tan Ao Ren Jian Li College of Computer Science Chongqing University Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China School of Electrical Engineering Chongqing University Chongqing China

data Distribution Service (DDS) is a widely-used middleware for data transmission in distributed real-time applications, such as autonomous vehicles and robotics. However, the communication of existing DDS middlewares generally relies on the network stacks of the operating system, which brings long latency to the real-time applications. In this paper, we propose a DPDK-based DDS, dubbed 3DS, to improve the performance of communication of DDS middlewares. First, 3DS reduces the latency of communication between distributed real-time applications by avoiding the latency of kernel. Second, 3DS reduces the overhead of dynamic memory allocation and deallocation by a reserved memory pool. Finally, 3DS adopts a thread-exclusive CPU model to reduce the resource contention between threads. We implement and evaluate 3DS on real systems running Linux. The experimental results show that 3DS reduces 44% of the communication latency over FastDDS, which is the state-of-the-art DDS middleware used by ROS2. Moreover, the throughput of data transfer in 3DS can be 1.51 times that of FastDDS.

关键词： Three-dimensional displays Smart cities Instruction sets Distributed databases Throughput Real-time systems Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Neural Network Panning: Screening the Optimal Sparse Network Before Training

arXiv

引用

arXiv 2022年

作者： Kang, Xiatao Li, Ping Yao, Jiayi Li, Chengxi School of Computer and Communication Engineering Changsha University of Science and Technology China School of Computer Xidian University China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp China

Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses metrics to calculate weight scores for weight screening, and extends from the initial single-order pruning to iterative pruning. Through these works, we argue that network pruning can be summarized as an expressive force transfer process of weights, where the reserved weights will take on the expressive force from the removed ones for the purpose of maintaining the performance of original networks. In order to achieve optimal expressive force scheduling, we propose a pruning scheme before training called Neural Network Panning which guides expressive force transfer through multi-index and multi-process steps, and designs a kind of panning agent based on reinforcement learning to automate processes. Experimental results show that Panning performs better than various available pruning before training methods. Our code is made public at: https://***/kangxiatao/RLPanning. Copyright © 2022, 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

Scavenger: Better Space-Time Trade-Offs for Key-Value Separated LSM-trees

Scavenger: Better Space-Time Trade-Offs for Key-Value Separa...

引用

International Conference on data engineering

作者： Jianshun Zhang Fang Wang Sheng Qiu Yi Wang Jiaxin Ou Junxun Huang Baoquan Li Peng Fang Dan Feng Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology China Shenzhen Huazhong University of Science and Technology Research Institute Bytefrance Inc.

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Key- Value Stores (KVS) implemented with log- structured merge-tree (LSM-tree) have gained widespread ac-ceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space am-plification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV- separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB).

关键词： data engineering Compaction Indexes Optimization

来源：评论

学校读者我要写书评

暂无评论

Quantized Analog Beamforming Enabled Multi-task Federated Learning Over-the-air

arXiv

引用

arXiv 2025年

作者： Yao, Jiacheng Xu, Wei Zhu, Guangxu Yang, Zhaohui Huang, Kaibin Niyato, Dusit National Mobile Communications Research Laboratory Southeast University Nanjing China Purple Mountain Laboratories Nanjing China Shenzhen Research Institute of Big Data Shenzhen China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore

Over-the-air computation (AirComp) has recently emerged as a pivotal technique for communication-efficient federated learning (FL) in resource-constrained wireless networks. Though AirComp leverages the superposition property of multiple access channels for computation, it inherently limits its ability to manage inter-task interference in multi-task computing. In this paper, we propose a quantized analog beamforming scheme at the receiver to enable simultaneous multi-task FL. Specifically, inspiring by the favorable propagation and channel hardening properties of large-scale antenna arrays, a targeted analog beamforming method in closed form is proposed for statistical interference elimination. Analytical results reveal that the interference power vanishes by an order of O (1/Nr) with the number of analog phase shifters, Nr, irrespective of their quantization precision. Numerical results demonstrate the effectiveness of the proposed analog beamforming method and show that the performance upper bound of ideal learning without errors can be achieved by increasing the number of low-precision analog phase shifters. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Backdoor Attack with Sparse and Invisible Trigger

arXiv

引用

arXiv 2023年

作者： Gao, Yinghua Li, Yiming Gong, Xueluan Li, Zhifeng Xia, Shu-Tao Wang, Qian The Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou311200 China College of Computing and Data Science Nanyang Technological University 639798 Singapore The School of Computer Science Wuhan University China Tencent Data Platform Shenzhen518057 China The Research Center of Artificial Intelligence Peng Cheng Laboratory Shenzhen518000 China The School of Cyber Science and Engineering Wuhan University China

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threatening training-phase threat, leading to serious risks in DNN-based applications. In this paper, we revisit the trigger patterns of existing backdoor attacks. We reveal that they are either visible or not sparse and therefore are not stealthy enough. More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack. To address this problem, we formulate the trigger generation as a bi-level optimization problem with sparsity and invisibility constraints and propose an effective method to solve it. The proposed method is dubbed sparse and invisible backdoor attack (SIBA). We conduct extensive experiments on benchmark datasets under different settings, which verify the effectiveness of our attack and its resistance to existing backdoor defenses. The codes for reproducing main experiments are available at https://***/YinghuaGao/SIBA. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Shared Incentive System for Clinical Pathway Experience

Shared Incentive System for Clinical Pathway Experience

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Weiqi Dai Wenhao Zhao Xia Xie Song Wu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China 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 Computer Science and Technology Hainan University Haikou China

The phenomenon of unbalanced regional medical resources has led to large differences in the implementation experience of clinical pathways in hospitals with different medical levels. However, due to the fear of privacy leakage and the lack of sharing motivation, there is a lack of effective collaborative communication channels for clinical pathways among medical institutions. In response to these problems, we propose a blockchain-based sharing incentive scheme for clinical pathway experience, which uses the clinical pathway implementation effect evaluation system to evaluate the quality of clinical pathway experience data. Specifically, we designe a two-phase cross-domain shared transaction model for the transaction of clinical pathway experience data. Moreover, we introduce the shared transaction alliance committee to verify and review the transaction, and solve the problems in the transaction in the arbitration phase. Finally, the functional test results show that the system meets the experience sharing incentive requirements, and the performance test results show that the TPS of sharing clinical pathway experience read and writed can reach around 600 and 1000, and the transaction latency of each phase is within 3 s.

关键词： Privacy Hospitals Collaboration Communication channels data models Security Incentive schemes

来源：评论

学校读者我要写书评

暂无评论

Weak Network Oriented Mobile Distributed Storage: A Hybrid Fault-Tolerance Scheme Based on Potential Replicas

Weak Network Oriented Mobile Distributed Storage: A Hybrid F...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Xinlei Wei Yujuan Tan Duo Liu Daitao Wu Yu Wu Xianzhang Chen Jian Li College of Computer Science Chongqing University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China School of Electrical Engineering Chongqing University Chongqing China

Node failure is one of the most typical issues in distributed storage systems. The classic fault-tolerance methods can meet the fault tolerance needs of systems deployed in edge storage, 5G IoT, and other high-performance data centers. However, mobile distributed systems contend with inconsistent network signals and relatively low bandwidth in weak network environments. The traditional fault-tolerance schemes have difficulty ensuring distributed storage and data repair simultaneously, posing a considerable challenge to data storage reliability. To address this problem, we proposed a hybrid fault-tolerance scheme based on potential replicas, called HFPR, which trades off storage overhead and performance for weak network mobile distributed storage systems. HFPR first stores data with the erasure code redundancy and then gradually increases data redundancy by reserving potential replicas, enabling the system to disperse network transmission pressure and reduce network transmission. To maximize replica utilization and control the storage overhead of potential replicas, we design a node state prediction mechanism and a file lifecycle management mechanism. Evaluation results show that, compared with the traditional hybrid fault-tolerant scheme with the same storage overhead, HFPR achieves better replica-level repair efficiency in data repair and a reduced probability of degraded reads by approximately 50%. During data distribution, HFPR can minimize data write amplification by up to 1.1× and additional network transfers by up to 77.5%.

关键词： data centers Fault tolerant systems Redundancy Distributed databases Memory Bandwidth Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

A Zero-shot Learning Method with a Multi-Modal Knowledge Graph

A Zero-shot Learning Method with a Multi-Modal Knowledge Gra...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Yuhong Zhang Haitao Shu Chenyang Bu Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Zero-shot learning aims to recognize unseen-classes using some seen-class samples as training set. It is challenging owing to that the feature representations of unseen-class samples are unavailable. Existing methods transfer the mapping from seen-classes to unseen-classes with the correlation as a bridge, in which, the semantic representations are used to discriminate the classes. However, the unavailability of visual representations for unseen-classes and the insufficient discrimination of semantic representations make the zero-shot learning challenging. Therefore, the visual representations are learned as complements to semantic representations to construct a multi-modal knowledge graph (KG), and a zero-shot learning method based on multi-modal KG is proposed in this paper. Specially, a semantic KG is introduced to capture the correlation of classes, and with the correlation, the visual feature representations of all classes are learned. Then, the discriminative visual representations and the semantic representations are used together to construct a multi-modal KG. With the multi-modal KG, the classifier for seen-classes is transferred to unseen classes. Extensive experimental results show the effectiveness of our method.

关键词： Learning systems Representation learning Training Bridges Visualization Correlation Semantics

来源：评论

学校读者我要写书评

暂无评论

Graph Sampling based Fairness-aware Recommendation over Sensitive Attribute Removal

Graph Sampling based Fairness-aware Recommendation over Sens...

引用

IEEE International Conference on data Mining (ICDM)

作者： Shenghao Liu Guoyang Wu Xianjun Deng Hongwei Lu Bang Wang Laurence Yang James J. Park Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea

Discrimination against different user groups has received growing attention in the recommendation field. To address this problem, existing works typically remove sensitive attributes that may cause discrimination through adversary learning to achieve fair recommendations. However, these approaches leverage all available interactions for learning user representations and overlook the fact that different interactions have varying relevance to users’ sensitive attributes. Ignoring this issue may weaken the effectiveness of adversary learning in removing sensitive attributes. To tackle this challenge, we propose a novel model called GS-FairRec, which distinguishes between user interactions to achieve better removal of sensitive attributes. The model consists of three modules: graph sampling-based representation learning, pseudo-user representation learning, and adversarial learning. Firstly, the graph sampling-based representation learning module removes some irrelevant neighbors from a user-item bipartite graph and employs a graph convolutional network (GCN) to learn user/item representations. Next, items that are relevant to a user’s sensitive information but do not match their preferences are defined as the user’s pseudo-interest items, which are leveraged to learn the pseudo-user representation. In the adversarial learning module, the user’s two kinds of representations are fused for adversarial learning to remove sensitive information. Additionally, we design a new metric to measure the model’s ability to remove sensitive attributes based on how a generated recommendation list discloses the user’s sensitive attributes. Finally, we conduct experiments on two real-world datasets, and our results demonstrate the superiority of our proposed model in fairness tasks.

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：