检索结果-内蒙古大学图书馆

17th IFIP WG 10.3 International Conference on Network and Parallel computing, NPC 2020

作者： Yu, Shuiying Wu, Sijie Chen, Hanhua Jin, Hai 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

ISBN: (纸本)9783030794774

The emergence of large-scale dynamic sets in real applications brings severe challenges in approximate set representation structures. A dynamic set with changing cardinality requires an elastic capacity of the approximate set representation structure, while traditional static structures, e.g., bloom filter, cuckoo filter, and their variants cannot satisfy the requirements. Existing dynamic approximate set representation structures only provide filter-level extensions, which require a single membership query to probe all discrete filters one by one. The large number of small discrete memory accesses takes up the vast majority of query time and results in unsatisfied query performance. To address the problem, in this work we propose the entry-extensible cuckoo filter (E2CF) to reduce memory access overhead for dynamic set representation and accelerate the membership query. E2CF utilizes adjacent buckets with continuous physical addresses in a cuckoo filter to extend bucket entries, which avoids many discrete memory accesses in a query. To further make E2CF space and time efficient, we adopt asynchronous extension and fine-grained splitting methods. Experiment results show that compared to state-of-the-art designs, E2CF reduces the query and insertion time by 82% and 28%, respectively. © 2021, IFIP International Federation for Information Processing.

关键词： data structures

来源：评论

学校读者我要写书评

暂无评论

Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge datacenters

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable computing 2025年

作者： Pei, Qiangyu Yuan, Yongjie Hu, Haichuan Wang, Lin Zhang, Dong Yan, Bingheng Yu, Chen Liu, Fangming 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 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Jinan Inspur Data Co. Ltd. China Huazhong University of Science and Technology Peng Cheng Laboratory China

The proliferation of deep-learning-based mobile and IoT applications has driven the increasing deployment of edge datacenters equipped with domain-specific accelerators. The unprecedented computing power offered by these accelerators puts a heavy burden on the cooling system, motivating more potent cooling techniques like cold water cooling. However, we observe that cold water cooling results in significant energy waste in edge datacenters due to the fluctuating resource utilization both spatially and temporally. To tackle this issue, we propose the concept of "working smarter"by slowing down accelerators deliberately whenever possible and enabling warm water cooling during these times to achieve cooling efficiency. Based on this concept, we develop Hyco - a hybrid water cooling system tailored for edge datacenters running deep learning workloads. First, Hyco features a zone-based cooling architecture enabling dynamic switching between cold water and warm water cooling. Then, based on a lightweight latency estimation method, Hyco incorporates a learning-based scheduling scheme to determine "which"accelerator workers and "when"to slow down through an adaptive and intelligent power-latency trade-off for deep learning models. The simulation with real-world traces shows that Hyco reduces the cooling energy consumption by up to 34.74× while satisfying latency constraints more than 99% of the time for deep-learning-based applications. © 2016 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MSI-UNet: A Flexible UNet-Based Multi-Scale Interactive Framework for 3D Gastric Tumor Segmentation on CT Scans

MSI-UNet: A Flexible UNet-Based Multi-Scale Interactive Fram...

引用

IEEE International Symposium on Biomedical Imaging

作者： Heyun Chen Zifan Chen Jie Zhao Haoshen Li Jiazheng Li Yiting Liu Mingze Yuan Peng Bao Xinyu Nan Bin Dong Lei Tang Li Zhang Center for Data Science Peking University China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Peking University Cancer Hospital&Institute China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Accurate segmentation of gastric tumors is critical yet presents a formidable challenge in medical imaging, where conventional UNet-based frameworks, despite their prevalence, falter on intricate tumor samples due to their limited interactive capacities. The SAM-based segmentation methods address this shortcoming yet with insufficient accuracy. By ingeniously blending images with mask inputs, our MSI-UNet leverages a U-shaped design to deliver pixel-perfect segmentation accuracy, while a novel multi-scale attention module adeptly harnesses interaction points for refined information extraction. When benchmarked on gastric tumor segmentation tasks, MSI-UNet surpasses existing state-of-the-art methods, elevating the Dice Similarity Coefficient (DSC) from 74.82% to 79.3% and minimizing Average Surface Distance (ASD) from 6.46 to 1.98, achieving a comparable accuracy with inter-radiologist consistency of 79.7% DSC. Furthermore, our framework demonstrates superior predictive prowess in survival analysis, enhancing the C-index from 61.7% to 68.68%. Ample experimental comparisons have substantiated that MSI-UNet holds the potential to offer considerable assistance to healthcare professionals in managing and decoding subsequent medical procedures.

关键词： Image segmentation Accuracy Three-dimensional displays Medical services Predictive models Information retrieval Decoding

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Large Recommendation Model Training with Near CXL Memory Processing

Enabling Efficient Large Recommendation Model Training with ...

引用

Annual International Symposium on Computer Architecture, ISCA

作者： Haifeng Liu Long Zheng Yu Huang Jingyi Zhou Chaoqiang Liu Runze Wang Xiaofei Liaot Hai Jinf Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab Huazhong University of Science and Technology China School of Computer Science and Engineering University of New South Wales Australia Zhejiang Lab Hangzhou China

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Personalized recommendation systems have become one of the most important Internet services nowadays. A critical challenge of training and deploying the recommendation models is their high memory capacity and bandwidth demands, with the embedding layers occupying hundreds of GBs to TBs of storage. The advent of memory disaggregation technology and Compute Express Link (CXL) provides a promising solution for memory capacity scaling. However, relocating memory-intensive embedding layers to CXL memory incurs noticeable performance degradation due to its limited transmission bandwidth, which is significantly lower than the host memory bandwidth. To address this, we introduce ReCXL, a CXL memory disaggregation system that utilizes near-memory processing for scalable, efficient recommendation model training. ReCXL features a unified, hardwareefficient NMP architecture that processes the entire embedding training within CXL memory, minimizing data transfers over the bandwidth-limited CXL and enhancing internal bandwidth. To further improve the performance, ReCXL incorporates softwarehardware co-optimizations, including sophisticated dependencyfree prefetching and fine-grained update scheduling, to maximize hardware utilization. Evaluation results show that ReCXL outperforms the CPU-GPU baseline and the naïve CXL memory by $7.1 \times \sim 10.6 \times(9.4 \times$ on average) and $12.7 \times \sim 31.3 \times(22.6 \times$ on average), respectively.

关键词： Training Degradation Scalability Prefetching Memory management Web and internet services Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Projection methods with linesearch technique for pseudomonotone equilibrium problems and fixed point problems

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第1期83卷 3-14页

作者： Zhu, Li-Jun Yao, Yonghong Postolache, Mihai The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province North Minzu University Yinchuan750021 China Health Big Data Research Institute of North Minzu University Yinchuan750021 China The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province North Minzu University Yinchuan750021 China Health Big Data Research Institute of North Minzu University Yinchuan750021 China School of Mathematical Sciences Tiangong Uni-versity Tianjin300387 China Center for General Education China Medical University Taichung40402 Taiwan Department of Interior Design Asia University Taichung Taiwan Romanian Academy Gh. Mihoc-C. Iacob Institute of Mathematical Statistics and Applied Mathematics Bucharest050711 Romania University "Politehnica" of Bucharest Department of Mathematics and Informatics Bucharest060042 Romania

In this paper, we discuss pseudomonotone equilibrium problems and fixed point problems in real Hilbert spaces. With the help of linesearch technique, we propose a projection algorithm without any Lipschitz-type condition for solving equilibrium problems and fixed point problems. We show that the constructed algorithm converges strongly to a common element of the investigated problems. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Image Report Generation Through Regional and Global Feature Interaction 2nd

Enhancing Medical Image Report Generation Through Regional a...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Teng, Pengrui Yang, Hongyu Zhang, Qinhu Ningbo Institute of Digital Twin Eastern Institute of Technology Tongxin Road No. 568 Zhuangshi Street Zhejiang Ningbo315201 China Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China University of Science and Technology of China No. 96 Jinzhai Road Baohe District Anhui Hefei230022 China

ISBN: (纸本)9789819619061

Medical image report generation has gained significant attention as an essential task in automated diagnosis, aiming to reduce the workload of physicians and expedite the diagnostic process. However, existing methods predominantly rely on coarse-grained global features, neglecting the fine-grained regional analysis. This limitation potentially leads to the loss of crucial diagnostic information. To address this challenge, we propose the Regional-Global Interaction Network (RGI), an innovative architecture designed to provide more granular information to the model. The RGI introduces two key components: (1) a region selection agent that precisely locates and selects relevant image patches based on input regional word embeddings, and (2) a bidirectional cross-attention mechanism that fuses the selected regional features with global features. This approach enables the model to capture local details while retaining global context. Extensive experiments on the IU X-Ray dataset demonstrate that our RGI architecture significantly improves the accuracy of medical image analysis and report generation. The proposed method outperforms existing state-of-the-art models across multiple evaluation metrics, including BLEU and ROUGE scores. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

LLM Knows Geometry Better than Algebra: Numerical Understanding of LLM-Based Agents in A Trading Arena

arXiv

引用

arXiv 2025年

作者： Ma, Tianmi Du, Jiawei Huang, Wenxin Wang, Wenjie Xie, Liang Zhong, Xian Zhou, Joey Tianyi Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computing National University of Singapore Singapore School of Science Wuhan University of Technology China

Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks. However, their ability to generalize to dynamic, unseen tasks, particularly in numerical reasoning, remains a challenge. Existing benchmarks mainly evaluate LLMs on problems with predefined optimal solutions, which may not align with real-world scenarios where clear answers are absent. To bridge this gap, we design the Agent Trading Arena, a virtual numerical game simulating complex economic systems through zero-sum games, where agents invest in stock portfolios. Our experiments reveal that LLMs, including GPT-4o, struggle with algebraic reasoning when dealing with plain-text stock data, often focusing on local details rather than global trends. In contrast, LLMs perform significantly better with geometric reasoning when presented with visual data, such as scatter plots or K-line charts, suggesting that visual representations enhance numerical reasoning. This capability is further improved by incorporating the reflection module, which aids in the analysis and interpretation of complex data. We validate our findings on NASDAQ STOCK dataset, where LLMs demonstrate stronger reasoning with visual data compared to text. Our code and data are publicly available at https://***/wekjsdvnm/***. © 2025, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A multi-dimensional index for privacy-preserving queries in cloud computing

A multi-dimensional index for privacy-preserving queries in ...

引用

作者： Xu, Hui Ding, Xiaofeng Jin, Hai Yu, Qing 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

Although cloud computing saves the cost of enterprises and individuals to manage data in various applications on public cloud servers, it also causes the problem of the leakage of critical personal information and sensitive data. Therefore, the issues about data privacy of the published personal information have become a challenging problem. Most of the existing methods focus on cryptography-based techniques by encrypting the sensitive data before publishing. However, these techniques are either too computation expensive or only some authorized users can get access to the encrypted cloud data. The consequence is that the search response time is not satisfactory and the sharing extent of the cloud data is becoming limited. Motivated by this, we propose a perturbation-based method to preserve the privacy of data in cloud. To accelerate the query processing without privacy breaches, a high-efficiency multi-dimensional index is built for answering range counting queries under differential privacy, which embeds privacy-preserving R-tree index in Content Addressable Network. Experimental results demonstrate that our methods not only protect data privacy in different degree, but also accelerate the query speed efficiently. Compared with the existing method Quad-opt, our method provides about 20% better data utility under the same differential privacy principles. © 2019 John Wiley & Sons, Ltd.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

EFFICIENTLY PARAMETERIZED NEURAL METRIPLECTIC SYSTEMS

arXiv

引用

arXiv 2024年

作者： Gruber, Anthony Lee, Kookjin Lim, Haksoo Park, Noseong Trask, Nathaniel Center for Computing Research Sandia National Laboratories AlbuquerqueNM United States School of Computing and Augmented Intelligence Arizona State University TempeAZ United States Big Data Analytics Laboratory Yonsei University Seoul Korea Republic of Big Data Analytics Laboratory Korea Advanced Institute of Science and Technology Daejeon Korea Republic of School of Engineering and Applied Science University of Pennsylvania PhiladelphiaPA United States

Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy conserving and entropy stable, the proposed approach comes with approximation results demonstrating its ability to accurately learn metriplectic dynamics from data as well as an error estimate indicating its potential for generalization to unseen timescales when approximation error is low. Examples are provided which illustrate performance in the presence of both full state information as well as when entropic variables are unknown, confirming that the proposed approach exhibits superior accuracy and scalability without compromising on model expressivity. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph for Science: From API based Programming to Graph Engine based Programming for HPC

arXiv

引用

arXiv 2023年

作者： Zhang, Yu Wang, Zixiao Zhao, Jin Guo, Yuluo Yu, Hui Huang, Zhiying Shi, Xuanhua Liao, Xiaofei 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

Modern scientific applications predominantly run on large-scale computing platforms, necessitating collaboration between scientific domain experts and high-performance computing (HPC) experts. While domain experts are often skilled in customizing domain-specific scientific computing routines, which often involves various matrix computations, HPC experts are essential for achieving efficient execution of these computations on large-scale platforms. This process often involves utilizing complex parallel computing libraries tailored to specific matrix computation scenarios. However, the intricate programming procedure and the need for deep understanding in both application domains and HPC poses significant challenges to the widespread adoption of scientific computing. In this research, we observe that matrix computations can be transformed into equivalent graph representations, and that by utilizing graph processing engines, HPC experts can be freed from the burden of implementing efficient scientific computations. Based on this observation, we introduce a graph engine-based scientific computing (Graph for Science) paradigm, which provides a unified graph programming interface, enabling domain experts to promptly implement various types of matrix computations. The proposed paradigm leverages the underlying graph processing engine to achieve efficient execution, eliminating the needs for HPC expertise in programming large-scale scientific applications. We evaluate the performance of the developed graph compute engine for three typical scientific computing routines. Our results demonstrate that the graph engine-based scientific computing paradigm achieves performance comparable to the best-performing implementations based on existing parallel computing libraries and bespoke implementations. Importantly, the paradigm greatly simplifies the development of scientific computations on large-scale platforms, reducing the programming difficulty for scientists and facilitating b

关键词： Application programming interfaces (API)

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：