检索结果-内蒙古大学图书馆

China Communications 2023年第3期 4-6页

作者： Shanzhi Chen F.Richard Yu Weisong Shi Changle Li China Information and Communication Technology Group Co. Ltd.(CICT) State Key Laboratory of Wireless Mobile Communications SMIC IEEE VTS Mobile World newsletter IEEE Canadian Academy of Engineering(CAE) Engineering Institute of Canada(EIC) IET Department of Computer and Information Sciences at the University of Delaware(UD) State Key Laboratory of Integrated Services Networks of Xidian University

With the development of new generation of information and communication technology, the Internet of Vehicles(Io V)/Vehicle-to-Everything(V2X), which realizes the connection between vehicle and X(i.e., vehicles, pedestrians, infrastructures, clouds, etc.), is playing an increasingly important role in improving traffic operation efficiency and driving safety as well as enhancing the intelligence level of social traffic services.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Heterogeneous Federated Learning with Multi-Level Prototypes

SSRN

引用

SSRN 2024年

作者： Guo, Shunxin Wang, Hongsong Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China MOE Key Laboratory of Computer Network and Information Integration China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Federated learning shows promise as a privacy-preserving collaborative learning technique. Existing research mainly focuses on skewing the label distribution across clients. However, most approaches suffer from catastrophic forgetting and classifier shift, mainly when the global distribution of all classes is extremely unbalanced and the data distribution of the client dynamically evolves over time. In this paper, we study the Dynamic Heterogeneous Federated Learning, which addresses the practical scenario where heterogeneous data distributions exist among different clients and dynamic tasks within the client. Accordingly, we propose a novel federated learning framework named Federated Multi-Level Prototypes and design federated multi-level regularizations. To mitigate classifier shift, we construct semantic prototypes to provide fruitful generalization knowledge. To maintain the model stability and consistency convergence, three regularizations are introduced as training losses, i.e., prototype-based regularization, semantic prototype-based regularization, and federated inter-task regularization. Extensive experiments show that the proposed method achieves advanced performance in various settings. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Complementary Classifier Induced Partial Label Learning

arXiv

引用

arXiv 2023年

作者： Jia, Yuheng Si, Chongjie Zhang, Min-Ling Key Laboratory of Computer Network and Information Integration School of Computer Science and Engineering Nanjing210096 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai200240 China

In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing works usually do not fully investigate the effectiveness of the non-candidate label set (a.k.a. complementary labels), which accurately indicates a set of labels that do not belong to a sample. In this paper, we use the non-candidate labels to induce a complementary classifier, which naturally forms an adversarial relationship against the traditional PLL classifier, to eliminate the false-positive labels in the candidate label set. Besides, we assume the feature space and the label space share the same local topological structure captured by a dynamic graph, and use it to assist disambiguation. Extensive experimental results validate the superiority of the proposed approach against state-of-the-art PLL methods on 4 controlled UCI data sets and 6 real-world data sets, and reveal the usefulness of complementary learning in PLL. The code has been released in the link https://***/Chongjie-Si/PL-CL. Copyright © 2023, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Parallel Optimization of Computational Fluid Dynamics Application code_saturne Based on Next Generation Sunway Supercomputer 14

Parallel Optimization of Computational Fluid Dynamics Applic...

引用

14th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2023

作者： Liu, Anjun Liao, Yin Xu, Xihao Chen, YanYan Zhong, Hongjun Wu, Jianming Kong, Bo Raikov, Alexander Guo, Meng Jinan Institute of Supercomputing Technology Jinan Key Laboratory of High Performance Industrial Software Jinan China Zhejiang Yuansuan Technology Co. Ltd Jinan Supercomputing-Zhejiang Yuansuan Industrial Simulation System Joint Laboratory Hangzhou China Qilu University of Technology Shandong Academy of Sciences Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Key Laboratory of Computing Power Network and Information Security China Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Shandong Jinan China

ISBN: (纸本)9798350371024

code_saturne is an open-source general large-scale computational fluid dynamics software independently developed by Electricite de France since 1997. Due to its high computing performance, code_saturne has been widely used in the nuclear industry, heavy fuel and biomass combustion, particle tracking and other computational fluid dynamics fields. In this work, we implemented code_saturne on the new generation Sunway supercomputer (SW26010pro) at the first time. By applying the data value-taking technology of double cache, combined with Sunway shared memory technology, we have adapted the data structure and Modular programming of code_saturne conducively to the new generation Sunway supercomputer (SW26010pro) and accelerated the software hotspots the software hotspots by 1-2 times. After optimizing and porting, this software has successfully served in the numerical simulation of the lateral flow of fuel assemblies in the nuclear industry. © 2023 IEEE.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Joint Waveform and Passive Beamforming Design for IRS-Aided ISAC via Deep Unfolding 16

Joint Waveform and Passive Beamforming Design for IRS-Aided ...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Zhang, Jifa Liu, Mingqian Tang, Jie Zhao, Nan Niyato, Dusit Wang, Xianbin School of Information and Communication Engineering Dalian University of Technology Dalian China Xidian University State Key Laboratory of Integrated Service Networks Xi'an China School of Electronic and Information Engineering South China University of Technology Guangzhou China School of Computer Science and Engineering Nanyang Technological University Singapore Western University Department of Electrical and Computer Engineering LondonONN6A 5B9 Canada

ISBN: (纸本)9798350390643

Integrated sensing and communication (ISAC) has become a promising technique to alleviate the spectrum congestion via sharing the same spectrum for communication and sensing. Nevertheless, many ISAC schemes encounter the challenges of high complexity. In this paper, we propose a dual-functional waveform design scheme for reconfigurable intelligent surface (RIS) aided ISAC based on deep unfolding learning. Specifically, the weighted sum of multi-user interference energy and waveform discrepancy is minimized via the joint waveform and phase-shift design. We first develop an alternating direction method of multipliers (ADMM) based iterative algorithm to handle the non-convex optimization problem. Then, we develop a deep unfolding neural network (NN), named ADMM-NET, which unfolds the proposed ADMM-based iterative algorithm to a layer-wise architecture. Simulation results verify the effectiveness of the proposed ADMM-NET. © 2024 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Throughput Analysis of SIC-Based Two-Device Slotted ALOHA with Feedback Over Nakagami-m Fading Channels 18

Throughput Analysis of SIC-Based Two-Device Slotted ALOHA wi...

引用

18th International Symposium on information Theory and Its Applications, ISITA 2024

作者： Fukui, Daiki Takahashi, Yuhei Song, Guanghui Kimura, Tomotaka Liu, Zilong Cheng, Jun Doshisha University Department of Intelligent Information Engineering and Sciences Kyoto610-0321 Japan Xidian University The State Key Laboratory of Integrated Services Networks Xi'an710071 China School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom

ISBN: (纸本)9784885523519

Throughput analysis for successive interference cancellation-based two-device slotted ALOHA with feedback is studied over Nakagami-m fading channels. Explicit expressions for the state transition probabilities are derived for a Markov process, thus facilitating the computation of the throughput. Through optimization of the transmission probability, it is shown that the maximum throughput is achieved for a given code rate. © 2024 The Institute of Electronics, information and Communication Engineers.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Semantic recommendation through Reinforcement Learning and weighted meta-paths

Semantic recommendation through Reinforcement Learning and w...

引用

2022 International Conference on Electronic information Engineering, Big Data, and computer Technology, EIBDCT 2022

作者： Yu, Jing Lang, Yue Li, Xuewen Zhang, Jin Zheng, Shaojie Gong, Jibing School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China Key Laboratory for Software Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

ISBN: (纸本)9781510655133

Explainable recommendation systems, which can produce high-accuracy recommendations and help users make quick decisions, have become a hotspot in research field. Most of existing research algorithms committed to improving the accuracy of recommendation, but ignored the interpretability of recommendation. We propose a semantic recommendation algorithm through Reinforcement Learning and weighted meta-paths which analyzes and selects the meta-path, and uses Reinforcement Learning network to train the weight of meta-path. This method can effectively solve data sparsity, improve the accuracy of recommendation, and increase interpretability. Compared with the baseline method, indicators of the recommended methods for integrating Reinforcement Learning with Heterogeneous information networks have been greatly improved, as verified and compared on a real MovieLens 1M dataset. Experimental results prove that the algorithm can effectively improve the accuracy and interpretability of the recommendation. © 2022 SPIE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

EAT: Towards Long-Tailed Out-of-Distribution Detection

arXiv

引用

arXiv 2023年

作者： Wei, Tong Wang, Bo-Lin Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-world scenarios. This paper addresses the challenging task of long-tailed OOD detection, where the in-distribution data follows a long-tailed class distribution. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes. To overcome this issue, we propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes. This approach allows us to build a detector with clear decision boundaries by training on OOD data using virtual labels. (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data. This technique encourages the model to pay more attention to the discriminative features of the tail classes. We provide a clue for separating in-distribution and OOD data by analyzing gradient noise. Through extensive experiments, we demonstrate that our method outperforms the current state-of-the-art on various benchmark datasets. Moreover, our method can be used as an add-on for existing long-tail learning approaches, significantly enhancing their OOD detection performance. Code is available at: https://***/Stomachache/Long-Tailed-OOD-Detection. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Spatial-Spectral Transformer for Local and Global Hyperspectral Image Classification

Spatial-Spectral Transformer for Local and Global Hyperspect...

引用

Signal, information and Data Processing (ICSIDP), IEEE International Conference on

作者： MengXin Cao Guixin Zhao Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Deep learning techniques have become increasingly prevalent in hyperspectral image (HSI) classification. However, convolutional neural network (CNN)-based approaches often struggle with inefficient utilization of spectral sequence data and inadequate processing of fine-grained spectral details. In contrast, transformer models are inherently designed to capture sequence dependencies across spectral bands. Yet, most existing approaches tend to focus on either local or global feature extraction separately, which limits their ability to fully exploit the spectral information. To overcome these limitations, we propose the Local and Global Fusion Spectral Transformer (LGFST), an innovative architecture that combines Swin Transformer blocks, standard Transformer blocks, and a novel Local-Global Fusion (LGF) module. This architecture is designed to simultaneously capture both local and global features, thereby improving the extraction of detailed spectral information. The Swin Transformer block, integrated with patch merging and hierarchical attention mechanisms, expands the receptive field and enhances local feature representation through both intra- and cross-window interactions. Meanwhile, the Transformer block performs self-attention across all tokens to extract global features. The fusion of local and global features from these two blocks effectively improves the texture and discriminative power of spectral data, leading to enhanced classification performance, especially in scenarios with dense class distributions. Finally, the LGF module facilitates interaction between local and global feature sets, ensuring a seamless integration of information from both blocks. Extensive experiments on three benchmark HSI datasets demonstrate that LGFST outperforms conventional transformer models and sets new benchmarks in performance compared to state-of-the-art methods.

关键词： Merging Benchmark testing Transformers Feature extraction Distortion Sensors Data mining Standards Hyperspectral imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

Long-tail learning with foundation model: heavy fine-tuning hurts 24

Long-tail learning with foundation model: heavy fine-tuning ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jiang-Xin Shi Tong Wei Zhi Zhou Jie-Jing Shao Xin-Yan Han Yu-Feng Li National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China School of Computer Science and Engineering Southeast University China and Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China

The fine-tuning paradigm in addressing longtail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified. In this paper, we disclose that heavy fine-tuning may even lead to nonnegligible performance deterioration on tail classes, and lightweight fine-tuning is more effective. The reason is attributed to inconsistent class conditions caused by heavy fine-tuning. With the observation above, we develop a low-complexity and accurate long-tail learning algorithms LIFT with the goal of facilitating fast prediction and compact models by adaptive lightweight fine-tuning. Experiments clearly verify that both the training time and the learned parameters are significantly reduced with more accurate predictive performance compared with state-of-the-art approaches. The implementation code is available at https://***/shijxcs/LIFT.

关键词：

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：