检索结果-内蒙古大学图书馆

22nd International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2022

作者： Zheng, Ran Jiang, Yingxin Wang, Yibo Su, Yongbo Zheng, Long Yao, Pengcheng Liao, Xiaofei 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 Wuhan430074 China Zhejiang Lab Hangzhou311121 China

ISBN: (纸本)9783031226762

Graph processing has evolved and expanded swiftly with artificial intelligence and big data technology. High-Bandwidth Memory (HBM), which delivers terabyte-level memory bandwidth, has opened up new development possibilities for FPGA-based graph accelerators. However, despite the tremendous expansion of underlying hardware capabilities, existing graph accelerators have not benefited too much. In this paper, we observe that the uniformed on-chip memory hierarchy is the key to the low scalability of existing graph accelerators. We present a novel graph accelerator with a distributed on-chip memory hierarchy called GraphS. The on-chip memory of GraphS is divided into numerous tiny blocks, each of which is assigned to only one Processing Element (PE). Different PEs are connected through a scalable network-on-chip (NoC). For realistic graphs with power-law properties, a degree-aware preprocessing method is designed to balance the workload among different PEs. Our results with various graph algorithms demonstrate that GraphS can outperform state-of-the-art ForeGraph by up to 21.84 ×. © 2023, Springer Nature Switzerland AG.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multiview Top-k Pooling with Deep-Q-Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2985-2996页

作者： Li, Zhi-Peng Su, Hai-Long Wu, Yong- Zhang, Qin-Hu Yuan, Chang-An Gribova, Valeriya Filaretov, Vladimir Fedorovich Huang, De-Shuang Eastern Institute of Technology Zhejiang Ningbo315201 China University of Science and Technology of China School of Life Sciences Anhui Hefei230026 China Tongji University Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Shanghai201804 China Guangxi Academy of Sciences Institute of Big Data and Intelligent Computing Research Center Nanning530007 China Far Eastern Branch of the Russian Academy of Sciences Institute of Automation and Control Processes Vladivostok690041 Russia

Graph neural networks (GNNs) are extensions of deep neural networks to graph-structured data. It has already attracted widespread attention for various tasks such as node classification and link prediction. Existing research focuses more on graph convolutional neural networks (GCNs). However, it is usually overlooked that graph pooling can obtain graph representations by summarizing and down-sampling node information. Meanwhile, existing graph pooling methods mainly use top-k for node selection, but most of them consider only single view information when scoring nodes, and the k values in top-k are usually selected empirically. This work proposes the hierarchical multiview top-k pooling (HMTPool) with deep-Q-networks, which scores nodes taking into account multiview information (considering graph structure and features) and does not rely on the empirical adaptive selection of the best k value. HMTPool is a two-stage process. It first uses a variant GCN and multilayer perceptron to score the nodes from structural and feature perspectives, respectively and then performs fusion operations on the multiview information scores of the nodes. In addition, to select the optimal pooling ratio of top-k, we propose a deep-Q-network-based top-k (DTop-k) node selection method, which can adaptively select the best pooling ratio without prior knowledge. Experimental results on six TUdatasets and two Benchmarking GNNs datasets demonstrate the effectiveness of our proposed approach. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

RIF-Proto: A Few-Shot Relation Extraction for Prototype Networks Based on Relational Information Features

RIF-Proto: A Few-Shot Relation Extraction for Prototype Netw...

引用

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Shuai Zhang Licai Wang Yangchen Huang Big data research and development center North China Institute of Computing Technology Beijing China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

Relation extraction stands as a core task within the realm of information extraction, focusing on identifying the target relations between entities in text. While traditional relation extraction has been extensively researched, certain relations lack sufficient labeled data, rendering traditional models ineffective in practical research. Hence, the research focus in this field has shifted towards few-shot learning methods that leverage limited labeled data for training. Significant progress has been made in few-shot relation extraction, with prototype networks garnering attention from scholars for their outstanding performance in few-shot tasks. Prototype networks utilize the clustering idea to achieve relationship classification simply and efficiently, and their training process is mainly divided into three parts: generation of relationship prototypes, relationship classification, and loss calculation. The majority of current research is centered around leveraging external information to enhance the generation of prototypes and loss functions, but due to the difficulty of obtaining external data and the high complexity of data processing, it greatly increases the time cost and the difficulty of implementation. Given the aforementioned challenges, this paper introduces a method for prototype refinement leveraging relationship similarity among existing data. This approach aims to effectively address the issue of significant deviations in relationship prototypes. Initially, extract relationship vectors from the instances in both the support set and query set, followed by computing the relationship similarity between samples based on these vectors, and finally, this paper constructs a prototype correction module, which utilizes the relationship similarity to assign weights to the samples in the support set, to achieve the purpose of prototype correction. In the experiments against the standard dataset FewRel1.0., we observe that the method substantially improves the ex

关键词： Training Seminars Semantics Prototypes Feature extraction Rendering (computer graphics) Vectors

来源：评论

学校读者我要写书评

暂无评论

A Novel Effectiveness Assessment Framework for Neoadjuvant Chemoradiotherapy of Locally Advanced Rectal Cancer Based on Multi-modal Intelligence

A Novel Effectiveness Assessment Framework for Neoadjuvant C...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tian, Xiao Sui, Dong Liu, Weifeng Guo, Maozu Luo, Gongning Wang, Kuanquan Beijing Key Laboratory for Intelligent Processing Methods of Architectural Big Data Beijing China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China Perceptual Computing Research Center Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350337488

Neoadjuvant chemoradiotherapy (nCRT) is the standard treatment for locally advanced rectal cancer (LARC). With the development of artificial intelligence, an increasing number of studies have begun to explore its application in cancer treatment prediction. However, the prior methods exhibit considerable variability even with slight modifications to the input data, which could potentially undermine the reliability of the results. In this paper, we proposed RP-Net, a novel multi-modal fusion-based framework that combines feature information from magnetic resonance imaging (MRI) and whole slide images (WSI), establishing a relationship to map the therapeutic effectiveness of nCRT for LARC. We investigated the relationship of the tumour region and its periphery tissues, and demonstrated the validity of the proposed framework that involving 11 different combinations of modalities. The experimental results revealed that it has achieved higher prediction accuracy compared to the four intra-categories single-modal combinations and outperformed the two intra-categories multi-modal combinations. When compared to the other four inter-categories multi-modal combinations, the fusion features get accuracy of 2% ∼ 6% improvement respectively. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Edge-based Joint User Association and Resource Allocation for Light Field Metaverse Systems

Edge-based Joint User Association and Resource Allocation fo...

引用

2023 IEEE International Conference on Metaverse computing, Networking and Applications, MetaCom 2023

作者： Wang, Chenchen Hu, Xinjue Zhang, Lin Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing China Wuhan University of Technology Intelligent Transportation System Research Center Wuhan China Beijing Big Data Center Beijing China

ISBN: (纸本)9798350333336

Light field (LF), as the representative of Metaverse multimedia format, its huge data scale and heavy rendering burden have brought great challenges to networks and user devices. Although edge-based light field Metaverse Systems can alleviate the enormous pressure of computing on users' devices, it will also make users need to pay additional charges of edge computing power and mobile data traffic for low-latency, high-quality light field Metaverse services. In this poster, we study the user association and bandwidth/computational resource allocation for multiple light field users connected to multiple edge nodes environment. An online Joint User Association and Resources Allocation (JUARA) optimization algorithm based on deep reinforcement learning is proposed, which can balance the service fee cost by users and response delay of LF service in a long-term time-varying network environment. The viewpoint rendering delay, data traffic fees and edge computing rental fees are evaluated in the simulation, and the results demonstrate the effectiveness of edge-assisted LF transmission architecture and proposed JUARA scheduling algorithm. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Labanotation generation based on motion capture data 5

Analysis of Labanotation generation based on motion capture ...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Chen, Boran Wang, Jiaji Miao, Zhenjiang Li, Jianpo Yang, Shengchun Jilin Electric Power Big Data Intelligent Processing Engineering Technology Research Center School of Computing Northeast Electric Power University Jilin Jilin132012 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781510668621

Labanotation is an approach to record human movement with different distributions in space that have different representations of symbols. Motion capture is a technique that records the trajectory of an object in the time domain by tracking the motion of key points, observed using different sensors, and recorded in files. This paper is to manually mark the Labanotation based on 3D human motion capture data, to divide the 3D human motion into gaits and poses, and to record and represent different human movements and positions in space in the notation. This is an exploration of motion capture data to generate Labanotation, while also contributing to the preservation of folk-art forms. © 2023 SPIE.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction 37

ES-Mask: Evolutionary Strip Mask for Explaining Time Series ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Sun, Yifei Song, Cheng Lu, Feng Li, Wei Jin, Hai Zomaya, Albert Y. 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 China Centre for Distributed and High Performance Computing School of Computer Science University of Sydney Australia

ISBN: (纸本)9781577358800

Machine learning models are increasingly used in time series prediction with promising results. The model explanation of time series prediction falls behind the model development and makes less sense to users in understanding model decisions. This paper proposes ES-Mask, a post-hoc and model-agnostic evolutionary strip mask-based saliency approach for time series applications. ES-Mask designs the mask consisting of strips with the same salient value in consecutive time steps to produce binary and sustained feature importance scores over time for easy understanding and interpretation of time series. ES-Mask uses an evolutionary algorithm to search for the optimal mask by manipulating strips in rounds, thus is agnostic to models by involving no internal model states in the search. The initial experiments on MIMIC-III data set show that ES-Mask outperforms state-of-the-art methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Novel 3D Medical Image Segmentation Model Using Improved SAM

A Novel 3D Medical Image Segmentation Model Using Improved S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Kuang, Yuansen Ma, Xitong Zhao, Jing Wang, Guangchen Zeng, Yijie Liu, Song Key Laboratory of Computing Power Network and Information Security Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

3D medical image segmentation is an essential task in the medical image field, which aims to segment organs or tumours into different labels. A number of issues exist with the current 3D medical image segmentation task: existing models cannot simultaneously obtain the space correlation and depth correlation of 3D slices;previous models suffer from local detail loss of positional embedding in 3D images;previous approaches often have blurring of boundaries in segmenting 3D images. To solve these shortcomings, we propose a 3D medical image segmentation model named TPM-SAM. In our model, we design a twinchannel image encoder to simultaneously capture the space correlation and depth correlation of 3D slices through a multi-head attention mechanism and improved adapters. Furthermore, we design a prompt encoding generator, which divides the volumetric image into small blocks and better captures the local detail information. In addition, we introduce a multi-layer aggregation decoder by employing U-Net with multi-level skip connection to solve the blurring of boundaries in processing 3D images. Finally, we experimented and evaluated our model on KiTS21 and LiTS17 datasets to compare with other baseline models. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Joint Pre-Encoding Representation and Sturcture Embedding for Efficient and Low-Resource Knowledge Graph Completion

Joint Pre-Encoding Representation and Sturcture Embedding fo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Qiu, Chenyu Qian, Pengjiang Wang, Chuang Yao, Jian Liu, Li Fang, Wei Ng, Eddie-Yin-Kwee School of Artificial Intelligence and Computer Science Jiangnan University China Engineering Research Center of Intelligent Technology for Healthcare Ministry of Education Jiangnan University China Big Data Center Affiliated Hospital of Jiangnan University China Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usage. In this paper, we propose Pre-Encoded Masked Language Model (PEMLM) to efficiently solve KGC problem. By encoding textual descriptions into semantic representations before training, the necessary resources are significantly reduced. Furthermore, we introduce a straightforward but effective fusion framework to integrate structural embedding with pre-encoded semantic description, which enhances the model's prediction performance on 1-N relations. The experimental results demonstrate that our proposed strategy attains state-of-the-art performance on the WN18RR (MRR+5.4% and Hits@1+6.4%) and UMLS datasets. Compared to existing models, we have increased inference speed by 30x and reduced training memory by approximately 60%. © 2024 Association for Computational Linguistics.

关键词： Knowledge graph

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：