检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Jinsong Jiang, Siyu He, Kun School of Computer Science and Technology Huazhong University of Science and Technology Institute of Artificial Intelligence Huazhong University of Science and Technology Hopcroft Center on Computing Science Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Hopcroft Center on Computing Science Huazhong University of Science and Technology Wuhan430074 China

Recently, the emerging graph Transformers have made significant advancements for node classification on graphs. In most graph Transformers, a crucial step involves transforming the input graph into token sequences as the model input, enabling Transformer to effectively learn the node representations. However, we observe that existing methods only express partial graph information of nodes through single-type token generation. Consequently, they require tailored strategies to encode additional graph-specific features into the Transformer to ensure the quality of node representation learning, limiting the model flexibility to handle diverse graphs. To this end, we propose a new graph Transformer called NTFormer to address this issue. NTFormer introduces a novel token generator called Node2Par, which constructs various token sequences using different token elements for each node. This flexibility allows Node2Par to generate valuable token sequences from different perspectives, ensuring comprehensive expression of rich graph features. Benefiting from the merits of Node2Par, NTFormer only leverages a Transformer-based backbone without graph-specific modifications to learn node representations, eliminating the need for graph-specific modifications. Extensive experiments conducted on various benchmark datasets containing homophily and heterophily graphs with different scales demonstrate the superiority of NTFormer over representative graph Transformers and graph neural networks for node classification. Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology 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 Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Transaction transmission model for blockchain channels based on non-cooperative games

引用

science China(Information sciences) 2023年第1期66卷 97-114页

作者： Peiyun ZHANG Chenxi LI Mengchu ZHOU Wenjun HUANG Abdullah ABUSORRAH Omaimah O.BAMASAG Engineering Research Center of Digital Forensics of Ministry of Education School of Computer and SoftwareNanjing University of Information Science and Technology School of Computer and Information Anhui Normal University Department of Electrical and Computer Engineering New Jersey Institute of Technology Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering and K.A.CARE Energy Research and Innovation CenterKing Abdulaziz University Department of Computer Science Faculty of Computing and Information Technology Center of Excellence in Smart Environment Research King Abdulaziz University

In blockchain networks, transactions can be transmitted through channels. The existing transmission methods depend on their routing information. If a node randomly chooses a channel to transmit a transaction, the transmission may be aborted due to insufficient funds(also called balance) or a low transmission rate. To increase the success rate and reduce transmission delay across all transactions, this work proposes a transaction transmission model for blockchain channels based on non-cooperative game *** balance, channel states, and transmission probability are fully considered. This work then presents an optimized channel transaction transmission algorithm. First, channel balances are analyzed and suitable channels are selected if their balance is sufficient. Second, a Nash equilibrium point is found by using an iterative sub-gradient method and its related channels are then used to transmit transactions. The proposed method is compared with two state-of-the-art approaches: Silent Whispers and Speedy Murmurs. Experimental results show that the proposed method improves transmission success rate, reduces transmission delay,and effectively decreases transmission overhead in comparison with its two competitive peers.

关键词： Blockchain channel transaction transmission channel balance channel state channel transmission probability non-cooperative game

来源：评论

学校读者我要写书评

暂无评论

RON-based cross-chain routing optimization strategy in metaverse

IET Blockchain

引用

IET Blockchain 2024年第4期4卷 379-392页

作者： Huang, Junjie Tan, Liang Xiao, Jianmei College of Computer Science Sichuan Normal University Sichuan Chengdu China Information Technology Center Sichuan Rural Credit Sichuan Chengdu China Institute of Computing Technology Chinese Academy of Sciences Beijing China Science and Innovation Center Deyang Jinshajianglu School Sichuan Deyang China

Metaverse is a new ecology that integrates the digital world with the physical world, generates a mirror image of the real world based on digital twin technology, and guarantees the fairness of the virtual world through the trusted mechanism of blockchain. Cross-chain communication technology is the key to realizing data circulation and collaborative processing between blockchains, which provides the communication foundation for the massive connection of blockchains in the metaverse. The current cross-chain communication mode is dominated by direct-connect routing, leading to network congestion and high propagation delay once the direct-connect link fails and cannot be recovered quickly. To optimize direct-connect routing, this paper proposed a cross-chain routing optimization strategy based on RON (Resilient Overlay Network), that is, Cross-Chain_RON, which firstly applies RON to reconstruct the direct-connect routing model, and then selects the optimal link through the shortest-path algorithm and policy routing, and combines with the RON performance database to improve the data transmission efficiency. Finally, the two communication modes were simulated by simulation tools. The experiments show that Cross-Chain_RON outperforms the direct-connect routing in terms of latency, rate of successful data transmission, and throughput in poor network environments, but at the expense of a certain amount of system overhead. © 2024 The Author(s). IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and technology.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DT-UPD: User Privacy Data Protection Through Distribution Transformation in Unlearning Cloud Service 24th

DT-UPD: User Privacy Data Protection Through Distribution Tr...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Sun, Shouyue Wu, Feng Zhang, Yingzhi Cui, Lei Gao, Longxiang Yu, Shui Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China School of Computer Science University of Technology Sydney Ultimo Australia

ISBN: (纸本)9789819615476

Providing machine unlearning services to users in the cloud, known as Machine Unlearning as a Service (MUaaS), has become a prominent privacy protection strategy. However, existing methods primarily focus on the effectiveness of the unlearning algorithm itself, while neglecting the privacy of the data users upload to the cloud for unlearning. To address this problem, we propose a distribution transformation method that maps users’ private data to a distribution (DT-UPD) that is functionally parallel and orthogonal to the original distribution. We then sample from this transformed distribution and use the sampled data instead of the original data to obtain the unlearning service. In detail, DT-UPD first employs the information bottleneck theory to extract the most relevant features for the unlearning service and then maps these features to a normal distribution. Low-dimensional features are then randomly sampled from this normal distribution and expanded into a high-dimensional space using adversarial reconstruction. This sampling and adversarial reconstruction process removes most of the information from the original private data (including unlearning-related and irrelevant information), ensuring that the final reconstructed data used for the unlearning service has a privacy protection effect. Additionally, we introduce Elastic Weight Consolidation (EWC) loss, which effectively avoids ‘catastrophic unlearning’ during the unlearning process. Extensive experimental results show that DT-UPD can achieve a forgetting accuracy (forget ACC) of 18.22% in the forgetting set with no more than a 6% accuracy loss in the test set. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Rethinking Tokenized Graph Transformers for Node Classification

arXiv

引用

arXiv 2025年

作者： Chen, Jinsong Li, Chenyang Li, GaiChao hopcroft, John E. He, Kun School of Computer Science and Technology Huazhong University of Science and Technology China Hopcroft Center on Computing Science Huazhong University of Science and Technology China Department of Computer Science Cornell University United States

Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which transforms the input graph into token sequences, facilitating the node representation learning via Transformer. In this paper, we observe that the generations of token sequences in existing GTs only focus on the first-order neighbors on the constructed similarity graphs, which leads to the limited usage of nodes to generate diverse token sequences, further restricting the potential of tokenized GTs for node classification. To this end, we propose a new method termed SwapGT. SwapGT first introduces a novel token swapping operation based on the characteristics of token sequences that fully leverages the semantic relevance of nodes to generate more informative token sequences. Then, SwapGT leverages a Transformer-based backbone to learn node representations from the generated token sequences. Moreover, SwapGT develops a center alignment loss to constrain the representation learning from multiple token sequences, further enhancing the model performance. Extensive empirical results on various datasets showcase the superiority of SwapGT for node classification. © 2025, CC BY.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

The Impact of Domain Name Server(DNS)over Hypertext Transfer Protocol Secure(HTTPS)on Cyber Security:Limitations,Challenges,and Detection Techniques

引用

computers, Materials & Continua 2024年第9期80卷 4513-4542页

作者： Muhammad Dawood Shanshan Tu Chuangbai Xiao Muhammad Haris Hisham Alasmary Muhammad Waqas Sadaqat Ur Rehman Faculty of Information Technology Beijing University of TechnologyBeijing100124China National Center of Robotics and Automation University of Engineering and TechnologyPeshawar25000Pakistan Department of Computer Science College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia School of Computing and Engineering Sciences Faculty of Engineering and ScienceUniversity of GreenwichLondonSE109LSUnited Kingdom School of Engineering Edith Cowan UniversityPerthWA 6027Australia School of Computer Science and Engineering University of SalfordManchesterM54BRUnited Kingdom

The DNS over HTTPS(Hypertext Transfer Protocol Secure)(DoH)is a new technology that encrypts DNS traffic,enhancing the privacy and security of ***,the adoption of DoH is still facing several research challenges,such as ensuring security,compatibility,standardization,performance,privacy,and increasing user *** significantly impacts network security,including better end-user privacy and security,challenges for network security professionals,increasing usage of encrypted malware communication,and difficulty adapting DNS-based security ***,it is important to understand the impact of DoH on network security and develop newprivacy-preserving techniques to allowthe analysis of DoH traffic without compromising user *** paper provides an in-depth analysis of the effects of DoH on *** discuss various techniques for detecting DoH tunneling and identify essential research challenges that need to be addressed in future security ***,this paper highlights the need for continued research and development to ensure the effectiveness of DoH as a tool for improving privacy and security.

关键词： DNS DNS over HTTPS cybersecurity machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Road Damage Detection and Infrastructure Evaluation Leveraging Unmanned Aerial Vehicles and Tiny Machine Learning

引用

IEEE Internet of Things Journal 2024年第12期11卷 21347-21358页

作者： Khan, Muhammad Waseem Obaidat, Mohammad S. Mahmood, Khalid Batool, Dania Badar, Hafiz Muhammad Sanaullah Aamir, Muhammad Gao, Wu Comsats University Islamabad Sahiwal Campus Department Of Computer Science Sahiwal57000 Pakistan Superior University Department Of Computer Science Lahore54000 Pakistan The University Of Jordan King Abdullah Ii School Of Information Technology Amman11942 Jordan University Of Science And Technology Beijing School Of Communication And Computing Engineering Beijing100083 China Amity University Amity School Of Engineering And Technology Uttar Pradesh Noida201301 India National Yunlin University Of Science And Technology Graduate School Of Intelligent Data Science Douliu64002 Taiwan University Of Palermo Department Of Engineering Palermo90133 Italy Emerson University Department Of Emerging Computing Technologies Multan60000 Pakistan Northwestern Polytechnical University Center For Bio-Inspired System-on-Chip School Of Computer Science Xi'an710060 China

Road damage detection (RDD) through computer vision and deep learning techniques can ensure the safety of vehicles and humans on the roads. Integrating unmanned aerial vehicles (UAVs) in RDD and infrastructure evaluation (IE) has also emerged as a key enabler, contributing significantly to data acquisition and real-time monitoring of road damages, such as potholes, cracks, and surface anomalies, facilitating proactive maintenance and improved road conditions. These UAVs are low-powered and resource-constrained devices that work autonomously to perform pattern detection and decision making leveraging tiny machine learning (Tiny ML) algorithms. These Tiny ML algorithms are designed to run on edge devices, IoT devices, UAVs, etc. In this study, the RDD2022 data set collected using UAVs and dashboard cameras of vehicles was utilized to train pure and mixed models that exhibit class instance imbalance in certain classes which is addressed by implementing data augmentation as a regularization technique. State-of-the-art two-stage detectors: Faster R-CNN ResNet101 and one-stage detectors: SSD MobileNet V1 FPN, YOLOv5, and Efficientdet D1 are employed. The results indicate that the two-stage detector achieved an impressive mean average precision (mAP) of 88.49% overall and 96.62% for focused classes. Notably, the state-of-the-art Efficientdet D1 approach achieved a competitive mAP of 86.47% overall and 95.12% for focused classes, with significantly lower computational cost. These findings highlight the potential of advanced object detection techniques, particularly Efficientdet D1, to enhance the accuracy and efficiency of RDD systems, thereby improving passenger safety and overall performance. © 2014 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective 32

How to Select Pre-Trained Code Models for Reuse? A Learning ...

引用

32nd IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2025

作者： Bi, Zhangqian Wan, Yao Chu, Zhaoyang Hu, Yufei Zhang, Junyi Zhang, Hongyu Xu, Guandong Jin, Hai Services Computing Technology and System Lab Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (纸本)9798331535100

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is compu-tationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks. © 2025 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Towards optimized tensor code generation for deep learning on sunway many-core processor

引用

Frontiers of computer science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

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

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

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：