检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Jin, Xiongnan Wang, Zhilin Chen, Jinpeng Yang, Liu Oh, Byungkook Hwang, Seung-Won Li, Jianqiang National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Alibaba Group China School of Computer Science Beijing University of Posts and Telecommunications China Xiangjiang Laboratory China School of Computer Science and Engineering Central South University China Computer Science & Engineering Konkuk University South Korea Department of Computer Science and Engineering Seoul National University South Korea

ISBN: (纸本)157735897X

Entity alignment (EA) is crucial for integrating knowledge graphs (KGs) constructed from diverse sources. Conventional unsupervised EA approaches attempt to eliminate human intervention but often suffer from accuracy limitations. With the rise of large language models (LLMs), leveraging their capabilities for EA presents a promising direction. However, it introduces new challenges: formulating the LLM-based EA problem and extracting the background knowledge in LLMs to realize EA without human intervention. This paper proposes HLMEA, a novel hybrid language model-based unsupervised EA method. HLMEA formulates the EA task into a filtering and single-choice problem and synergistically integrates small language models (SLMs) and LLMs. Specifically, SLMs filter candidate entities based on textual representations generated from KG triples. Then, LLMs refine this selection to identify the most semantically aligned entities. An iterative self-training mechanism allows SLMs to distill knowledge from LLM outputs, enhancing the EA ability of hybrid language models in subsequent rounds cooperatively. We also conducted extensive experiments on benchmark datasets to evaluate HLMEA's performance. The results demonstrate that HLMEA significantly outperforms unsupervised and even supervised EA baselines, proving its potential for scalable and effective EA across large KGs. The code and data are available at https://***/xnjin-ai/HLMEA. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient data Prefetch Strategy for Deep Learning Based on Non-volatile Memory 15th

An Efficient Data Prefetch Strategy for Deep Learning Based ...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Jiang, Wenbin Liu, Pai Jin, Hai Peng, Jing 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 Wuhan430074 China

ISBN: (纸本)9783030642426

Deep learning (DL) systems usually utilize asynchronous prefetch to improve data reading performance. However, the efficiency of the data transfer path from hard disk to DRAM is still limited by disk performance. The emerging non-volatile memory (NVRAM) provides a novel solution for this problem, while few existing researches have considered it. We propose a novel efficient data prefetch strategy for DL based on a heterogeneous memory system combining NVRAM with DRAM. Benefitting from the large capacity and fast reading speed of NVRAM, the strategy uses an asynchronous reading method named sliding NVRAM cache (SNC) to improve the performance of the data transfer paths. A sliding window is applied to map the data from disk to NVRAM and continuously update the data, while non-ideal writing performance of NVRAM can be remitted to a large extent in this strategy. Experiments show that SNC can improve the time performance of diverse deep neural networks training by more than 30%. © 2020, Springer Nature Switzerland AG.

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection 39

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Dist...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Lin, Yang Guo, Hang Wang, Jinbao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching

arXiv

引用

arXiv 2024年

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

BED: A Block-Level Deduplication-Based Container Deployment Framework 15th

BED: A Block-Level Deduplication-Based Container Deployment ...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Zhang, Shiqiang Wu, Song Fan, Hao Zou, Deqing 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 Scinece and Technology Wuhan430074 China

ISBN: (纸本)9783030642426

Container technology has gained great popularity in cloud environment since containers provide near-native performance and are lighter and less expensive than traditional virtual machines. However, starting up a non-local container, whose image is unavailable locally, is time-consuming. The reason is that pulling an image from a remote registry requires a long time. In this paper, we experimentally find that a lot of redundant data exists among image layers when we pull images from the registry. This redundant data causes additional pull time and makes the startup of a non-local container slower. To minimize the amount of pulled data while providing intact images, we propose a container deployment framework, BED, based on block-level deduplication. To be specific, BED stores an image layer as numerous data blocks and a fingerprint list which is generated based on these data blocks. When BED needs to pull an image, it pulls the fingerprint lists of the image, deduplicates these fingerprint lists, and pulls the data blocks non-existing locally from the registry. Based on the local and pulled blocks, BED reconstructs the image layers for a container. Experiments show that compared with original Docker, BED reduces the time of pulling images by 35% on average and saves about 48% data transmission in the network. © 2020, Springer Nature Switzerland AG.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Framework for Spatial Interpolation: Merging data-driven with Domain Knowledge

arXiv

引用

arXiv 2024年

作者： Zhang, Cong Du, Shuyi Song, Hongqing Wang, Yuhe National & Local Joint Engineering Lab for Big Data Analysis and Computing Technology Beijing100190 China School of Civil and Resource Engineering University of Science and Technology Beijing Beijing100083 China Institute for Scientific Computation Texas A&M University College StationTX77843 United States

Estimating spatially distributed information through the interpolation of scattered observation datasets often overlooks the critical role of domain knowledge in understanding spatial dependencies. Additionally, the features of these datasets are typically limited to the spatial coordinates of the scattered observation locations. In this paper, we propose a hybrid framework that integrates data-driven spatial dependency feature extraction with rule-assisted spatial dependency function mapping to augment domain knowledge. We demonstrate the superior performance of our framework in two comparative application scenarios, highlighting its ability to capture more localized spatial features in the reconstructed distribution fields. Furthermore, we underscore its potential to enhance nonlinear estimation capabilities through the application of transformed fuzzy rules and to quantify the inherent uncertainties associated with the observation datasets. Our framework introduces an innovative approach to spatial information estimation by synergistically combining observational data with rule-assisted domain knowledge. © 2024, CC BY.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

arXiv

引用

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Hardware-Supported Remote Persistence for Distributed Persistent Memory

Hardware-Supported Remote Persistence for Distributed Persis...

引用

Supercomputing Conference

作者： Zhuohui Duan Haodi Lu Haikun Liu Xiaofei Liao Hai Jin Yu Zhang Song Wu National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computing Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

The advent of Persistent Memory (PM) necessitates an evolution of Remote Direct Memory Access (RDMA) technologies for supporting remote data persistence. Previous software-based solutions require remote CPU intervention and postpone the visibility of remote persistence. In this paper, we design several hardware-supported RDMA primitives to flush data from the volatile cache of RDMA Network Interface Cards (RNICs) to the PM. We also propose durable RPCs based on the proposed RDMA Flush primitives to support remote data persistence and fast failure recovery. We emulate the performance of RDMA Flush primitives through other RDMA prim-itives, and compare our proposals with several state-of-the-art RPCs in a real testbed equipped with PM and InfiniBand networks. Experimental results show that our proposals can improve the throughput of RPCs by up to 90%, and reduce the 99th percentile latency by up to 49%. The experimental studies also provide instructive guidelines for designing RDMA-based distributed PM systems.

关键词： High performance computing Throughput Proposals Network interfaces Guidelines

来源：评论

学校读者我要写书评

暂无评论

SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector

arXiv

引用

arXiv 2024年

作者： Mao, Qianchen Li, Qiang Wang, Bingshu Zhang, Yongjun Dai, Tao Chen, C.L. Philip The School of Software Northwestern Polytechnical University Taicang Campus Suzhou215400 China The School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou510641 China

In recent years, the detection of infrared small targets using deep learning methods has garnered substantial attention due to notable advancements. To improve the detection capability of small targets, these methods commonly maintain a pathway that preserves high-resolution features of sparse and tiny targets. However, it can result in redundant and expensive computations. To tackle this challenge, we propose SpirDet, a novel approach for efficient detection of infrared small targets. Specifically, to cope with the computational redundancy issue, we employ a new dual-branch sparse decoder to restore the feature map. Firstly, the fast branch directly predicts a sparse map indicating potential small target locations (occupying only 0.5% area of the map). Secondly, the slow branch conducts fine-grained adjustments at the positions indicated by the sparse map. Additionally, we design an lightweight DO-RepEncoder based on reparameterization with the Downsampling Orthogonality, which can effectively reduce memory consumption and inference latency. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models while achieving faster inference speed and fewer parameters. For example, on the IRSTD-1K dataset, SpirDet improves MIoU by 4.7 and has a 7× FPS acceleration compared to the previous state-of-the-art model. The code will be open to the public. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Whale: Efficient One-to-Many data Partitioning in RDMA-Assisted Distributed Stream Processing systems

Whale: Efficient One-to-Many Data Partitioning in RDMA-Assis...

引用

Supercomputing Conference

作者： Jie Tan Hanhua Chen Yonghui Wang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computing Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

To process large-scale real-time data streams, existing distributed stream processing systems (DSPSs) leverage different stream partitioning strategies. The one-to-many data partitioning strategy plays an important role in various applications. With one-to-many data partitioning, an upstream processing instance sends a generated tuple to a potentially large number of downstream processing instances. Existing DSPSs leverage an instance-oriented communication mechanism, where an upstream instance transmits a tuple to different downstream instances separately. However, in one-to-many data partitioning, multiple downstream instances typically run on the same machine to exploit multi-core resources. Therefore, a DSPS actually sends a data item to a machine multiple times, raising significant unnecessary costs for serialization and communication. We show that such a mechanism can lead to serious performance bottleneck due to CPU overload. To address the problem, we design and implement Whale, an efficient RDMA (Remote Direct Memory Access) assisted distributed stream processing system. Two factors contribute to the efficiency of this design. First, we propose a novel RDMA-assisted stream multicast scheme with a self-adjusting non-blocking tree structure to alleviate the CPU workloads of an upstream instance during one-to-many data partitioning. Second, we re-design the communication mechanism in existing DSPSs by replacing the instance-oriented communication with a new worker-oriented communication scheme, which saves significant costs for redundant serialization and communication. We implement Whale on top of Apache Storm and conduct comprehensive experiments to evaluate its performance with large-scale real world datasets. The results show that Whale achieves 56.6x improvement of system throughput and 97% reduction of processing latency compared to existing designs.

关键词： Costs Storms High performance computing Memory management Whales Distributed databases Throughput

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：