检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

RAHP: A Redundancy-aware Accelerator for High-performance Hypergraph Neural Network

RAHP: A Redundancy-aware Accelerator for High-performance Hy...

引用

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Hui Yu Yu Zhang Ligang He Yingqi Zhao Xintao Li Ruida Xin Jin Zhao Xiaofei Liao Haikun Liu Bingsheng He 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 Department of Computer Science University of Warwick United Kingdom National University of Singapore Singapore

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

Hypergraph Neural Network (HyperGNN) has emerged as a potent methodology for dissecting intricate multilateral connections among various entities. Current software/hardware solutions leverage a sequential execution model that relies on hyperedge and vertex indices for conducting standard matrix operations for HyperGNN inference. Yet, they are impeded by the dual challenges of redundant computation and irregular memory access overheads. This is primarily due to the frequent and repetitive access and updating of a number of feature vectors corresponding to the same hyperedges and vertices. To address these challenges, we propose the first redundancy-aware accelerator, RAHP, which enables high performance execution of HyperGNN inference. Specifically, we present a redundancy-aware asynchronous execution approach into the accelerator design for HyperGNN to reduce redundant computations and off-chip memory accesses. To unveil opportunities for data reuse and unlock the parallelism that existing HyperGNN solutions fail to capture, it prioritizes vertices with the highest degree as roots, prefetching other vertices along the hypergraph structure to capture the common vertices among multiple hyperedges, and synchronizing the computations of hyperedges and vertices in real-time. By such means, this facilitates the concurrent processing of relevant hyperedge and vertex computations of the common vertices along the hypergraph topology, resulting in smaller redundant computations overhead. Furthermore, by efficiently caching intermediate results of the common vertices, it curtails memory traffic and off-chip communications. To fully harness the performance potential of our proposed approach in the accelerator, RAHP incorporates a topology-driven data loading mechanism to minimize off-chip memory accesses on the fly. It is also endowed with an adaptive data synchronization scheme to mitigate the effects of conflicting updates of both hyperedges and vertices. Moreover, RAHP emplo

关键词： Computational modeling Neural networks Memory management Loading Energy conservation Vectors Software Topology Synchronization Standards

来源：评论

学校读者我要写书评

暂无评论

The Influence of the Implementation of Trade Facilitation Systems on the Time Required for Creating Delivery Orders: A Case Study of Tema Port

引用

World Journal of engineering and Technology 2024年第3期12卷 529-539页

作者： Justice Awosonviri Akodia Clement K. Dzidonu David King Boison Philip Kisembe Joseph Gbandi Advanced School of Systems and Data Studies Accra Institute of Technology Accra Ghana Department of Procurement Logistics and Supply Chain Management Ghana Communication Technology University Accra Ghana Department of Computer Engineering Ghana Communication Technology University Accra Ghana College of Education Ohio University Athens Ohio USA

This study evaluated the impact of Ghana’s Integrated Customs Management System (ICUMS), implemented within the National Single Window initiative, on the efficiency of issuing Delivery Orders (DO) at Tema Port. Filling a gap in the existing literature, the research employed a quantitative approach to assess a specific time-related aspect of the cargo clearance process. Employing an Independent t-test on a dataset spanning 2026 Delivery Orders (924 pre-ICUMS and 1102 post-ICUMS) from July 2020 to July 2023, the study investigated ICUMS’s effectiveness in reducing DO issuance time. Results indicate a noteworthy decrease in average DO issuance time, from 11 days pre-implementation to approximately 9 days post-implementation, a reduction validated by statistical analysis through the independent t-test. In light of these findings, the study recommends ongoing refinement of the implementation, reinforcement of trade facilitation measures, and the adoption of best practices from successful global ports. Continuous stakeholder training and regular assessments of ICUMS performance are also endorsed. The study’s implications support the theoretical framework for Single Window systems and carry significant policy implications, emphasizing the need for collaborative efforts to streamline trade facilitation processes driven by Information Technology. Practically, the results serve as a management tool for stakeholders, highlighting areas for targeted interventions to reduce DO issuance times. Methodologically, this research contributes by applying robust statistical analysis to a specific component within the Time Release Study framework, offering a nuanced understanding of trade facilitation systems’ effectiveness in improving cargo clearance processes.

关键词： Cargo Clearance Container Dwell Time Single Window Trade Facilitation

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning for Multi-turn Dialogue Generation with Topic Drift Modeling 12

Multi-task Learning for Multi-turn Dialogue Generation with ...

引用

12th IEEE International Conference on Big Knowledge, ICBK 2021

作者： Zeng, Hongwei Hong, Zhenjie Liu, Jun Wei, Bifan Xi'An Jiaotong University School of Computer Science and Technology Xi'an China Xi'An Jiaotong University National Engineering Lab For Big Data Analytics Xi'an China Xi'An Jiaotong University School of Continuing Education Xi'an China

ISBN: (纸本)9781665438582

Multi-turn dialogue generation aims to generate natural and fluent responses that should be consistent with multiple consecutive utterances history. It is a more challenging task compared to its single-turn counterpart since it requires the model to capture the topic drift along with the multi-turn dialogue history. In this paper, we propose a multi-turn dialogue generation model which incorporates topic drift aware information into a hierarchical encoder-decoder framework to generate coherent responses. This model first utilizes a Convolutional Neural Network (CNN) based topic model to obtain the topic representation of each utterance. Then a topic drift model is employed to encode the sequential topics of multi-turn dialogue history to infer the topic of response. During the response generation, a specially designed topic drift aware generator is proposed to dynamically balance the impact of the inferred topic of response and local word structure. Fur-thermore, we employ multi-task learning to optimize the topic drift model and dialogue generation simultaneously. Extensive experimental results on two benchmark datasets (i.e. Cornell Movie Dialog Corpus and Ubuntu Dialogue dataset) indicate that our proposed model can generate more coherent responses, and significantly outperform other dialogue generation models. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Informing Innovation Management: Linking Leading R&D Firms and Emerging Technologies

arXiv

引用

arXiv 2023年

作者： Gong, Xian McFarland, Claire McCarthy, Paul Griffith, Colin Rizoiu, Marian-Andrei Faculty of Engineering and Information Technology University of Technology SydneyNSW Australia Beesness Pty Ltd Australia The Data Science Institute University of Technology SydneyNSW Australia School of Computer Science and Engineering UNSW Sydney NSW Australia Australia

Understanding the relationship between emerging technology and research and development has long been of interest to companies, policy makers and researchers. In this paper new sources of data and tools are combined with a novel technique to construct a model linking a defined set of emerging technologies with the global leading R&D spending companies. The result is a new map of this landscape. This map reveals the proximity of technologies and companies in the knowledge embedded in their corresponding Wikipedia profiles, enabling analysis of the closest associations between the companies and emerging technologies. A significant positive correlation for a related set of patent data validates the approach. Finally, a set of Circular Economy Emerging Technologies are matched to their closest leading R&D spending company, prompting future research ideas in broader or narrower application of the model to specific technology themes, company competitor landscapes and national interest concerns. © 2023, CC BY-NC-SA.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

Energy-based Proportional Fairness in Cooperative Edge Computing

arXiv

引用

arXiv 2022年

作者： Vu, Thai T. Chu, Nam H. Phan, Khoa T. Hoang, Dinh Thai Nguyen, Diep N. Dutkiewicz, Eryk School of Engineering and Mathematical Sciences Department of Computer Science and Information Technology La Trobe University Melbourne Australia School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia

By executing offloaded tasks from mobile users, edge computing augments mobile devices with computing/communications resources from edge nodes (ENs), thus enabling new services/applications (e.g., real-time gaming, virtual/augmented reality). However, despite being more resourceful than mobile devices, allocating ENs’ computing/communications resources to a given favorable set of users (e.g., closer to edge nodes) may block other devices from their services. This is often the case for most existing task offloading and resource allocation approaches that only aim to maximize the network social welfare or minimize the total energy consumption but do not consider the computing/battery status of each mobile device. This work develops an energy-based proportionally fair task offloading and resource allocation framework for a multi-layer cooperative edge computing network to serve all user equipments (UEs) while considering both their service requirements and individual energy/battery levels. The resulting optimization involves both binary (offloading decisions) and continuous (resource allocation) variables. To tackle the NP-hard mixed integer optimization problem, we leverage the fact that the relaxed problem is convex and propose a distributed algorithm, namely the dynamic branch-and-bound Benders decomposition (DBBD). DBBD decomposes the original problem into a master problem (MP) for the offloading decisions and multiple subproblems (SPs) for resource allocation. To quickly eliminate inefficient offloading solutions, the MP is integrated with powerful Benders cuts exploiting the ENs’ resource constraints. We then develop a dynamic branch-and-bound algorithm (DBB) to efficiently solve the MP considering the load balance among ENs. The SPs can either be solved for their closed-form solutions or be solved in parallel at ENs, thus reducing the complexity. The numerical results show that the DBBD returns the optimal solution in maximizing the proportional fairness among U

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction

arXiv

引用

arXiv 2023年

作者： Luo, Haoran Haihong, E. Yang, Yuhao Yao, Tianyu Guo, Yikai Tang, Zichen Zhang, Wentai Peng, Shiyao Wan, Kaiyang Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh School of Computer Science Beijing University of Posts and Telecommunications China School of Automation Science and Electrical Engineering Beihang University China Beijing Institute of Computer Technology and Application China Inspur Group Co. Ltd. China College of Computing and Data Science Nanyang Technological University Singapore

Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities. To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction. We introduce a span-tuple classification approach with hetero-ordered merging and output merging to accomplish fine-grained n-ary relation extraction in different arity. Furthermore, Text2NKG supports four typical NKG schemas: hyper-relational schema, event-based schema, role-based schema, and hypergraph-based schema, with high flexibility and practicality. The experimental results demonstrate that Text2NKG achieves state-of-the-art performance in F1 scores on the fine-grained n-ary relation extraction benchmark. Our code and datasets are publicly available1 © 2023, CC BY-NC-SA.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

URL: Combating Label Noise for Lung Nodule Malignancy Grading

arXiv

引用

arXiv 2023年

作者： Ai, Xianze Liao, Zehui Xia, Yong Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China

Due to the complexity of annotation and inter-annotator variability, most lung nodule malignancy grading datasets contain label noise, which inevitably degrades the performance and generalizability of models. Although researchers adopt the label-noise-robust methods to handle label noise for lung nodule malignancy grading, they do not consider the inherent ordinal relation among classes of this task. To model the ordinal relation among classes to facilitate tackling label noise in this task, we propose a Unimodal-Regularized Label-noise-tolerant (URL) framework. Our URL contains two stages, the Supervised Contrastive Learning (SCL) stage and the Memory pseudo-labels generation and Unimodal regularization (MU) stage. In the SCL stage, we select reliable samples and adopt supervised contrastive learning to learn better representations. In the MU stage, we split samples with multiple annotations into multiple samples with a single annotation and shuffle them into different batches. To handle label noise, pseudo-labels are generated using the similarity between each sample and the central feature of each class, and temporal ensembling is used to obtain memory pseudo-labels that supervise the model training. To model the ordinal relation, we introduce unimodal regularization to keep the ordinal relation among classes in the predictions. Moreover, each lung nodule is characterized by three orthographic views. Experiments conducted on the LIDC-IDRI dataset indicate the superiority of our URL over other competing methods. Code is available at https://***/axz520/URL. © 2023, CC BY-NC-ND.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

A Unified Analysis for Finite Weight Averaging

arXiv

引用

arXiv 2024年

作者： Wang, Peng Shen, Li Tao, Zerui Sun, Yan Zheng, Guodong Tao, Dacheng School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China School of Cyber Science & Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China RIKEN Center for Advanced Intelligence Project Tokyo Japan Faculty of Engineering The University of Sydney Australia School of Computer and Data Science Nanyang Technological University Singapore

Averaging iterations of Stochastic Gradient Descent (SGD) have achieved empirical success in training deep learning models, such as Stochastic Weight Averaging (SWA), Exponential Moving Average (EMA), and LAtest Weight Averaging (LAWA). Especially, with a finite weight averaging method, LAWA can attain faster convergence and better generalization. However, its theoretical explanation is still less explored since there are fundamental differences between finite and infinite settings. In this work, we first generalize SGD and LAWA as Finite Weight Averaging (FWA) and explain their advantages compared to SGD from the perspective of optimization and generalization. A key challenge is the inapplicability of traditional methods in the sense of expectation or optimal values for infinite-dimensional settings in analyzing FWA’s convergence. Second, the cumulative gradients introduced by FWA introduce additional confusion to the generalization analysis, especially making it more difficult to discuss them under different assumptions. Extending the final iteration convergence analysis to the FWA, this paper, under a convexity assumption, establishes a convergence bound O(log (T/k) /√T), where k ∈ [1, T/2] is a constant representing the last k iterations. Compared to SGD with O(log(T)/√T), we prove theoretically that FWA has a faster convergence rate and explain the effect of the number of average points. In the generalization analysis, we find a recursive representation for bounding the cumulative gradient using mathematical induction. We provide bounds for constant and decay learning rates and the convex and non-convex cases to show the good generalization performance of ***, experimental results on several benchmarks verify our theoretical results. © 2024, CC BY.

关键词： Stochastic systems

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：