检索结果-内蒙古大学图书馆

Cacomp: A Cloud-assisted Collaborative Deep Learning Compiler Framework for DNN Tasks on Edge

IEEE Transactions on computers 2025年

作者： Lin, Weiwei Lin, Jinhui Zhang, Haotong Wu, Wentai Wu, Weizheng Li, Zhetao Li, Keqin South China University of Technology School of Computer Science and Engineering Guangzhou510641 China Pengcheng Laboratory Shenzhen518066 China South China University of Technology School of Software Engineering Guangzhou510641 China Jinan University Department of Computer Science College of Information Science and Technology Guangzhou510632 China Jinan University College of Information Science and Technology Guangzhou510632 China State University of New York Department of Computer Science New PaltzNY12561 United States

With the development of edge computing, DNN services have been widely deployed on edge devices. The deployment efficiency of deep learning models relies on the optimization of inference and scheduling policy. However, traditional optimization methods on edge devices still suffer from prohibitively long tuning time due to devices’ low computational power. Meanwhile, the widely used scheduling algorithm, the dominant resource fairness algorithm(DRF algorithm), struggles to maximize the efficiency of model execution on edge devices and inevitably increases average waiting time as it is not applicable in the real-time distributed computing environment. In this paper, we propose Cacomp, a distributed cloud-assisted deep learning compiler framework that features accelerating the optimization on edge devices with assistance from the cloud and a novel inference task scheduling algorithm. Our framework utilizes the tuning records from the cloud devices and proposes a two-step distillation strategy to obtain the best tuning record set for the edge device. For the scheduling process, we propose an RD-DRF algorithm to allocate inference tasks to edge devices based on dominant resource matching in real time. Extensive results show that our framework can achieve up to 2.19× improvement in the optimization time compared with other methods on edge devices. Our proposed scheduling algorithm significantly shortens the average waiting time of inference tasks by 30% and improves resource utilization by 20% on edge devices. © 1968-2012 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

AGConv: Adaptive Graph Convolution on 3D Point Clouds

arXiv

引用

arXiv 2022年

作者： Wei, Mingqiang Wei, Zeyong Zhou, Haoran Hu, Fei Si, Huajian Chen, Zhilei Zhu, Zhe Qiu, Jingbo Yan, Xuefeng Guo, Yanwen Wang, Jun Qin, Jing School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Hong Kong Polytechnic University Hong Kong

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic limitation of poor distinctive feature learning. In this paper, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis. AGConv generates adaptive kernels for points according to their dynamically learned features. Compared with the solution of using fixed/isotropic kernels, AGConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts. Unlike the popular attentional weight schemes, AGConv implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points. Extensive evaluations clearly show that our method outperforms state-of-the-arts of point cloud classification and segmentation on various benchmark datasets. Meanwhile, AGConv can flexibly serve more point cloud analysis approaches to boost their performance. To validate its flexibility and effectiveness, we explore AGConv-based paradigms of completion, denoising, upsampling, registration and circle extraction, which are comparable or even superior to their competitors. Our code is available at https://***/hrzhou2/AdaptConv-master. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Weighted Density for The Win: Accurate Subspace Density Clustering

Weighted Density for The Win: Accurate Subspace Density Clus...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Maixuan Peng Yuyang Wu Yang Lu Mengke Li Yiqun Zhang Yiu-Ming Cheung School of Computer Science and Technology Guangdong University of Technology Guangzhou China Faculty of Science Wilfrid Laurier University Brantford Canada Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

k-clustering typically struggles with the detection of irregular-distributed clusters due to the natural bias, while density clustering usually cannot well-adapt to different datasets and clustering tasks as it is not an oriented optimization process. This paper, therefore, proposes to perform density clustering in dynamically learned subspaces. To exploit the irregular-distributed clusters obtained by density clustering for the subspace determination, we design a new strategy to appropriately evaluate the importance of attributes. It turns out that the proposed Weighted Density-based Subspace Clustering (WDSC) algorithm inherits the unbiased merits of density clustering, and also upgrades the unlearning density clustering to be learnable under the subspace learning paradigm of k-clustering. A comprehensive evaluation including significance tests, ablation studies, qualitative comparisons, etc., shows the superiority of WDSC.

关键词： Accuracy Heuristic algorithms Signal processing algorithms Clustering algorithms Signal processing Acoustics Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Assisted key Generation Electric Health Records Sharing Scheme 8th

A Blockchain-Assisted Key Generation Electric Health Records...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Zhang, Qiao Chen, Xiubo Ahmad, Haseeb Xu, Gang Yang, Yixian Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University Guiyang Guizhou550025 China State Key Laboratory of Networking and Switching Technology Information Security Center Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science National Textile University Faisalabad37610 Pakistan School of Information Science and Technology North China University of Technology Beijing100144 China

ISBN: (纸本)9783031067631

Electronic health records (EHRs) contain a large amount of private data of patients. Once these data are compromised during the process of sharing, it may threaten the patients’ privacy. In this paper, a novel blockchain-assisted electronic health record sharing scheme is proposed, which utilizes attribute-based encryption (ABE) based on the consortium blockchain to realize the privacy protection in the sharing process of EHRs. Firstly, the master key is negotiated by all consensus nodes of consortium blockchain, no one knows the specific value of the master key. Consensus nodes are acted by medical institutions, they also responsible for generating and managing users’ private keys. Secondly, with the help of powerful cloud services, pre-decryption and ciphertext retrieval assignments are outsourced to cloud services for reducing the burden of blockchain. Thirdly, this scheme is also based on searchable encryption, which allows for quick ciphertext lookup from cloud services. Data owners can generate ciphertext indexes for their private data, and data users with retrieval trapdoors can quickly retrieve ciphertexts. Finally, the security and performance of blockchain-assisted electronic health record sharing scheme are analyzed in detail, the results show that our scheme is safe and feasible. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs 39

CLDG: Contrastive Learning on Dynamic Graphs

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Critical Node Detection Using Neural Network-based Initialization in a Genetic Algorithm

arXiv

引用

arXiv 2024年

作者： Liu, Chanjuan Ge, Shike Chen, Zhihan Pei, Wenbin Zhu, Enqiang Mei, Yi Ishibuchi, Hisao The School of Computer Science and Technology Dalian University of Technology 116024 China The Institute of Software Chinese Academy of Science Beijing100190 China The Institute of Computing Science and Technology Guangzhou University Guangzhou510006 China The School of Engineering and Computer Science Victoria University of Wellington Wellington6012 New Zealand The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

The Critical Node Problem (CNP) is concerned with identifying the critical nodes in a complex network. These nodes play a significant role in maintaining the connectivity of the network, and removing them can negatively impact network performance. CNP has been studied extensively due to its numerous real-world applications. Among the different versions of CNP, CNP-1a has gained the most popularity. The primary objective of CNP-1a is to minimize the pair-wise connectivity in the remaining network after deleting a limited number of nodes from a network. Due to the NP-hard nature of CNP-1a, many heuristic/metaheuristic algorithms have been proposed to solve this problem. However, most existing algorithms start with a random initialization, leading to a high cost of obtaining an optimal solution. To improve the efficiency of solving CNP-1a, a knowledge-guided genetic algorithm named K2GA has been proposed. Unlike the standard genetic algorithm framework, K2GA has two main components: a pretrained neural network to obtain prior knowledge on possible critical nodes, and a hybrid genetic algorithm with local search for finding an optimal set of critical nodes based on the knowledge given by the trained neural network. The local search process utilizes a cut node-based greedy strategy. The effectiveness of the proposed knowledge-guided genetic algorithm is verified by experiments on 26 real-world instances of complex networks. Experimental results show that K2GA outperforms the state-of-the-art algorithms regarding the best, median, and average objective values, and improves the best upper bounds on the best objective values for eight real-world instances. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

INNSE: Invertible neural network-based DNA image storage with self-correction encoding

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2492-2502页

作者： Zheng, Yanfen Zhang, Xiaokang Sun, Lijun Cao, Ben Wang, Bin Zhang, Qiang Zheng, Pan School of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China The Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Liaoning Dalian116622 China Department of Accounting and Information Systems University of Canterbury Upper Riccarton Christchurch8140 New Zealand

DNA storage has become an alternative to silicon-based storage of media. However, when used to store multimodal data such as images, it fails to take full advantage of the characteristics of high correlation and variability present in such data, and currently remains inferior in terms of encoding density and time complexity. It also has the shortcoming of weak performance in terms of error correction methods to address insertion and deletion errors caused by error crosstalk. Therefore, we proposed an invertible neural network-based DNA image storage self-correction encoding method (INNSE) that uses the invertibility of network to perform up-down sampling processing on image and video data, thereby greatly reducing the number of DNA sequences required for data storage. A codebook generator was then designed to encode low-dimensional vectors into DNA sequences that meet various constraints. Finally, a self-correction method was constructed to achieve DNA sequence error correction at the base level without adding any redundant information. Our experimental results showed that, compared to the Yin-Yang algorithm, the encoding density of INNSE was increased by 3×, encoding time complexity was reduced by 95.26%. Under a simulated error rate of 2%, PSNR and SSIM were raised by 80.88% and 63.82%, respectively, proving that INNSE has significant advantages in encoding performance and error correction ability. © 2025

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

SCBench: A Sports Commentary Benchmark for Video LLMs

arXiv

引用

arXiv 2024年

作者： Ge, Kuangzhi Chen, Lingjun Zhang, Kevin Luo, Yulin Shi, Tianyu Fan, Liaoyuan Li, Xiang Wang, Guanqun Zhang, Shanghang State Key Laboratory of Multimedia Information Processing School of Computer Science Peking University China Department of Computer Science University of Toronto Canada The University of Hong Kong Hong Kong Southern University of Science and Technology China

Recently, significant advances have been made in Video Large Language Models (Video LLMs) in both academia and industry. However, methods to evaluate and benchmark the performance of different Video LLMs, especially their fine-grained, temporal visual capabilities, remain very limited. On one hand, current benchmarks use relatively simple videos (e.g., subtitled movie clips) where the model can understand the entire video by processing just a few frames. On the other hand, their datasets lack diversity in task format, comprising only QA or multi-choice QA, which overlooks the models' capacity for generating in-depth and precise texts. Sports videos, which feature intricate visual information, sequential events, and emotionally charged commentary, present a critical challenge for Video LLMs, making sports commentary an ideal benchmarking task. Inspired by these challenges, we propose a novel task: sports video commentary generation, developed SCBench for Video LLMs. To construct such a benchmark, we introduce (1) SCORES, a six-dimensional metric specifically designed for our task, upon which we propose a GPT-based evaluation method, and (2) CommentarySet, a dataset consisting of 5,775 annotated video clips and ground-truth labels tailored to our metric. Based on SCBench, we conduct comprehensive evaluations on multiple Video LLMs (e.g. VILA, Video-LLaVA, etc.) and chain-of-thought baseline methods. Our results found that InternVL-Chat-2 achieves the best performance with 5.44, surpassing the second-best by 1.04. Our work provides a fresh perspective for future research, aiming to enhance models' overall capabilities in complex visual understanding tasks. Our dataset will be released soon. © 2024, CC BY-NC-ND.

关键词： Footage counters

来源：评论

学校读者我要写书评

暂无评论

Multi-block-single-probe variance reduced estimator for coupled compositional optimization 22

Multi-block-single-probe variance reduced estimator for coup...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Wei Jiang Gang Li Yibo Wang Lijun Zhang Tianbao Yang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science the University of Iowa Iowa City Department of Computer Science and Engineering Texas A&M University College Station

ISBN: (纸本)9781713871088

Variance reduction techniques such as SPIDER/SARAH/STORM have been extensively studied to improve the convergence rates of stochastic non-convex optimization, which usually maintain and update a sequence of estimators for a single function across iterations. What if we need to track multiple functional mappings across iterations but only with access to stochastic samples of O(1) functional mappings at each iteration? There is an important application in solving an emerging family of coupled compositional optimization problems in the form of ∑mi=1 fi(gi(w)), where gi is accessible through a stochastic oracle. The key issue is to track and estimate a sequence of g(w) = (g1(w),..., gm(w)) across iterations, where g(w) has m blocks and it is only allowed to probe O(1) blocks to attain their stochastic values and Jacobians. To improve the complexity for solving these problems, we propose a novel stochastic method named Multi-block-Single-probe Variance Reduced (MSVR) estimator to track the sequence of g(w). It is inspired by STORM but introduces a customized error correction term to alleviate the noise not only in stochastic samples for the selected blocks but also in those blocks that are not sampled. With the help of the MSVR estimator, we develop several algorithms for solving the aforementioned compositional problems with improved complexities across a spectrum of settings with non-convex/convex/strongly convex/Polyak-Łojasiewicz (PL) objectives. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on the strong convexity parameter. Empirical studies on multi-task deep AUC maximization demonstrate the better performance of using the new estimator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Dataflow Runtime Environment of DFC 1

引用

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Zhang, Jing Li, Jinrong Du, Zheng Shu, Jiwu Luo, Qiuming NHPCC/Guangdong Key Laboratory of Popular HPC College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9783030692445

ISBN: (纸本)9783030692438

In this paper, we introduce the DFC dataflow language and its runtime environment. DFC runtime library is in charge of constructing the DAG of the dataflow graph, firing the DFC tasks and the synchronizations between the tasks of successive passes. Basing on an elaborately implemented thread pool and queued Active Data, DFC runtime shows an ideal performance comparing with DSPatch. The experiment of a simple dataflow graph shows that DFC has better performance for the cases that the parallelism beneath the core number, while DSPatch shows a better scalability for the cases of the parallelism exceed the core number. As DFC is still a prototype language, it lacks the ability to construct the DAG dynamically, which leads to low efficiency when coding for a well-structured dataflow graph. © 2021, Springer Nature Switzerland AG.

关键词： Data flow analysis

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：