检索结果-内蒙古大学图书馆

Enhancing the Uplink of Cell-Free Massive MIMO Through Prioritized Sampling and Personalized Federated Deep Reinforcement Learning

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Mendoza, Charmae Franchesca Kaneko, Megumi Rupp, Markus Schwarz, Stefan Technische Universität Wien Institute of Telecommunications Sustainable Radio Access Networks Christian Doppler Laboratory Digital Twin Assisted AI Vienna1040 Austria National Institute of Informatics Information Systems Architecture Science Research Division Tokyo101-8430 Japan Department of Computer Science University of Tokyo Tokyo Japan Technische Universität Wien Institute of Telecommunications Vienna1040 Austria

Effective power control is key to solving the inter-user interference problem that degrades performance in cell-free massive multiple-input multiple-output (MIMO) systems. Motivated by its ability to operate online and model-free, without relying on training datasets, we leverage deep reinforcement learning (DRL) for uplink power control, aiming to maximize the guaranteed rate. We propose a fully centralized single-agent framework and two distributed schemes that employ several agents for improved scalability, leveraging prioritized experience replay to enable fast adaptation to the dynamic changes of the wireless environment. We investigate the performance of two multi-agent system architectures: (1) centralized training, decentralized execution (CTDE), where each agent forwards its RL experience to a central trainer, and (2) personalized federated learning (FedPer), where the training is performed locally at each agent, and only the base layer of the local deep neural network (DNN) model is forwarded periodically for aggregation at a server. We focus on the realistic scenario of dynamic device (de-)activation, combined with user mobility. Numerical evaluations demonstrate that the proposed FedPer with prioritized sampling achieves near-optimal rate and power performance while incurring the least amount of communication overhead. © 2015 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Dual-Branch Network Based on Wavelet Decomposition for Image Inpainting

An Dual-Branch Network Based on Wavelet Decomposition for Im...

引用

第43届中国控制会议

作者： Yuqing Shi Jiacheng Li Yang Zhang Shiqiang Du College of Electronic Engineering Northwest Minzu University Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Chinese National Information Technology Research Institute Northwest Minzu University College of Mathematics and Computer Science Northwest Minzu University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In this paper, we propose the Wavelet-Guided Dual-Branch Network(WGDN), an innovative deep learning framework designed for image inpainting. WGDN uniquely leverages wavelet decomposition to address the challenge of reconstructing large missing regions by analyzing both low-frequency and high-frequency subbands of the image. The structure branch focuses on the low-frequency subband to restore overall structure, while the texture branch reconstructs intricate details using three high-frequency subbands. Key enhancements include the integration of an Efficient Transformer Block(ETB) in the structure branch for global information capture and a Residual in Residual Dense Block(RRDB) in the texture branch for detailed texture recovery. Additionally, we employ the CIEDE2000 color difference formula to ensure color consistency in the restored *** extensive testing demonstrates that WGDN outperforms existing methods in both qualitative and quantitative measures,establishing new benchmarks for the field of image inpainting.

关键词： Image Inpainting Wavelet Transform Attention Mechanism Image Processing

来源：评论

学校读者我要写书评

暂无评论

Global scale solar energy harnessing: An advanced intra-hourly diffuse solar irradiance predicting framework for solar energy projects

引用

Neural Computing and Applications 2024年第18期36卷 10585-10598页

作者： El-kenawy, El-Sayed M. Bailek, Nadjem Bouchouicha, Kada Zerouali, Bilel Hassan, Muhammed A. Kuriqi, Alban Jamil, Basharat Colak, Ilhami Khalil, Adel Ibrahim, Abdelhameed Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura35111 Egypt Laboratory of Mathematics Modeling and Applications Department of Mathematics and Computer Science Faculty of Sciences and Technology Ahmed Draia University of Adrar Adrar01000 Algeria Energies and Materials Research Laboratory Faculty of Sciences and Technology University of Tamanghasset Tamanrasset10034 Algeria MEU Research Unit Middle East University Amman Jordan Adrar01000 Algeria Vegetal Chemistry-Water-Energy Laboratory Faculty of Civil Engineering and Architecture Department of Hydraulic Hassiba Benbouali University of Chlef Ouled Fares Chlef02180 Algeria Mechanical Power Engineering Department Faculty of Engineering Cairo University Giza12613 Egypt School of Architecture University of Waterloo 7 Melville St S CambridgeONN1S 2H4 Canada CERIS Instituto Superior Tecnico Universidade de Lisboa Lisbon Portugal Civil Engineering Department University for Business and Technology PristinaKosovo10000 High Temperature Processes Unit IMDEA Energy Institute Av. Ramón de La Sagra 3 Móstoles Madrid28935 Spain Faculty of Engineering and Architectures Nisantasi University Istanbul Turkey Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

Diffuse horizontal irradiance (DHI) forecasts are critical for adopting solar photovoltaic technology. Yet, they can lack reliability given the limited and uncertain meteorological data available for desert areas. This research develops a new sine cosine dipper throated optimization (SCDTO) technique, targeting DHI prediction even given such data constraints. SCDTO uniquely hybridizes sine cosine metaheuristics, adept at exploration, with dipper throat optimization, providing focused exploitation. This hybridization aims to create a robust ensemble model capable of delivering reliable DHI predictions despite climatic uncertainty. The ensemble model, employing various input combinations, was rigorously evaluated across multiple meteorological stations. The SCDTO algorithm exhibited remarkable performance improvements, yielding substantial reductions exceeding 93% in root mean squared error and 98% in mean absolute error at key stations in Morocco, including Tan-Tan, Zagora, Erfoud, and Oujda. Comparative analyses against established optimization algorithms consistently underscored the superior predictive capabilities of SCDTO. Visualizations, including box plots and histograms, demonstrated SCDTO’s efficacy in minimizing prediction errors, particularly for Tan-Tan, Zagora, and Erfoud stations. Also, statistical validation through one-way analysis of variance (ANOVA) further affirmed the significance of the proposed SCDTO method. Therefore, this hybrid metaheuristic optimization enables more accurate DHI predictions from limited meteorological data. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

From Hypergraph Energy Functions to Hypergraph Neural Networks

arXiv

引用

arXiv 2023年

作者： Wang, Yuxin Gan, Quan Qiu, Xipeng Huang, Xuanjing Wipf, David School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Amazon United States Peng Cheng Laboratory China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

Hypergraphs are a powerful abstraction for representing higher-order interactions between entities of interest. To exploit these relationships in making downstream predictions, a variety of hypergraph neural network architectures have recently been proposed, in large part building upon precursors from the more traditional graph neural network (GNN) literature. Somewhat differently, in this paper we begin by presenting an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings that, when paired with a parameterized classifier, can be trained end-to-end via a supervised bilevel optimization process. Later, we draw parallels between the implicit architecture of the predictive models emerging from the proposed bilevel hypergraph optimization, and existing GNN architectures in common use. Empirically, we demonstrate state-of-the-art results on various hypergraph node classification benchmarks. Code is available at https://***/yxzwang/PhenomNN. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Memory-facilitated Joint-space Shift Adaptation in Traffic Forecasting

Memory-facilitated Joint-space Shift Adaptation in Traffic F...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ye Wei He Haitao Gerald Schaefer Zhigang Ji Yifan Wang Hui Fang Department of Computer Science Loughborough University Loughborough UK The Alan Turing Institute London UK School of Architecture Building and Civil Engineering Loughborough University Loughborough UK National Key Laboratory of Science and Technology on Micro/Nano Fabrication Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Traffic forecasting, crucial for intelligent transport systems, faces significant challenges from distribution shifts due to the dynamic nature of traffic patterns. Although normalisation approaches have been proposed to address distribution shifts in other time-series forecasting tasks such as predicting electricity consumption load prediction or influenza-like illness patient number estimation, they fall short in handling the complex spatial and temporal shifts in traffic data. In this paper, we propose a novel memory-facilitated joint-space shift adaptation framework, ST-Align, to address this problem in traffic forecasting. ST-Align comprises two key components targeting the input and latent space, respectively: a memory-based data alignment module in the input space, and an end-to-end memory network structure dedicated to alignment within the latent space. This joint-space design enables our ST-Align framework to effectively capture and adapt to dynamic distribution shifts in both spatial and temporal dimensions, thus enhancing model performance. Extensive experiments on various real-world datasets and prediction backbones convincingly demonstrate the robustness and generalisability of our method.

关键词： Adaptation models Electricity Neural networks Estimation Traffic control Robustness Forecasting

来源：评论

学校读者我要写书评

暂无评论

DU-DARTS: Decreasing the Uncertainty of Differentiable architecture Search 32

DU-DARTS: Decreasing the Uncertainty of Differentiable Archi...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Lu, Shun Hu, Yu Yang, Longxing Sun, Zihao Mei, Jilin Zeng, Yiming Li, Xiaowei Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Tecent ADlab China

Differentiable Neural architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency. However, the competition of candidate operations in DARTS introduces high uncertainty for selecting the truly important operation, thus leading to serious performance collapse. In this work, we decrease the uncertainty of differentiable architecture search (DU-DARTS) by enforcing the distribution of architecture parameters to approach the one-hot categorical distribution and by replacing the zero operation with a gate switch. Without any extra search cost, our method achieves state-of-the-art performance with 2.32%, 16.74%, and 24.1% test error on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively. Moreover, DU-DARTS can robustly find an excellent architecture on NAS-Bench-1Shot1 and NAS-Bench-201, which further demonstrates the effectiveness of our method. The source code is available at https://***/ShunLu91/DU-DARTS. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding

arXiv

引用

arXiv 2024年

作者： Zhang, Chong Tu, Yi Zhao, Yixi Yuan, Chenshu Chen, Huan Zhang, Yue Chai, Mingxu Guo, Ya Zhu, Huijia Zhang, Qi Gui, Tao School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Ant Tiansuan Security Lab Ant Group Hangzhou China School of Statistics and Data Science Nankai University Tianjin China Institute of Modern Languages and Linguistics Fudan University Shanghai China

Modeling and leveraging layout reading order in visually-rich documents (VrDs) is critical in document intelligence as it captures the rich structure semantics within documents. Previous works typically formulated layout reading order as a permutation of layout elements, i.e. a sequence containing all the layout elements. However, we argue that this formulation does not adequately convey the complete reading order information in the layout, which may potentially lead to performance decline in downstream VrD tasks. To address this issue, we propose to model the layout reading order as ordering relations over the set of layout elements, which have sufficient expressive capability for the complete reading order information. To enable empirical evaluation on methods towards the improved form of reading order prediction (ROP), we establish a comprehensive benchmark dataset including the reading order annotation as relations over layout elements, together with a relation-extraction-based method that outperforms previous methods. Moreover, to highlight the practical benefits of introducing the improved form of layout reading order, we propose a reading-order-relation-enhancing pipeline to improve model performance on any arbitrary VrD task by introducing additional reading order relation inputs. Comprehensive results demonstrate that the pipeline generally benefits downstream VrD tasks: (1) with utilizing the reading order relation information, the enhanced downstream models achieve SOTA results on both two task settings of the targeted dataset;(2) with utilizing the pseudo reading order information generated by the proposed ROP model, the performance of the enhanced models has improved across all three models and eight cross-domain VrD-IE/QA task settings without targeted optimization. Copyright © 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

A New Paradigm of User-Centric Wireless Communication Driven by Large Language Models

arXiv

引用

arXiv 2025年

作者： Ding, Kuiyuan Guo, Caili Yang, Yang Hu, Wuxia Eldar, Yonina C. Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Beijing Laboratory of Advanced Information Net works School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

The next generation of wireless communications seeks to deeply integrate artificial intelligence (AI) with user-centric communication networks, with the goal of developing AI-native networks that more accurately address user requirements. The rapid development of large language models (LLMs) offers significant potential in realizing these goals. However, existing efforts that leverage LLMs for wireless communication often overlook the considerable gap between human natural language and the intricacies of real-world communication systems, thus failing to fully exploit the capabilities of LLMs. To address this gap, we propose a novel LLM-driven paradigm for wireless communication that innovatively incorporates the nature language to structured query language (NL2SQL) tool. Specifically, in this paradigm, user personal requirements is the primary focus. Upon receiving a user request, LLMs first analyze the user intent in terms of relevant communication metrics and system parameters. Subsequently, a structured query language (SQL) statement is generated to retrieve the specific parameter values from a high-performance real-time database. We further utilize LLMs to formulate and solve an optimization problem based on the user request and the retrieved parameters. The solution to this optimization problem then drives adjustments in the communication system to fulfill the user’s requirements. To validate the feasibility of the proposed paradigm, we present a prototype system. In this prototype, we consider user-request centric semantic communication (URC-SC) system in which a dynamic semantic representation network at the physical layer adapts its encoding depth to meet user requirements, such as improved data transmission quality or reduced data transmission latency. Additionally, two LLMs are employed to analyze user requests and generate SQL statements, respectively. Simulation results demonstrate the effectiveness of the prototype in personalizing and addressing user r

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs

arXiv

引用

arXiv 2024年

作者： Zhou, Xin Nie, Ping Guo, Yiwen Wei, Haojie Zhang, Zhanqiu Minervini, Pasquale Ma, Ruotian Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University Shanghai China LightSpeed Studios Tencent China Institute of Modern Languages and Linguistics Fudan University Shanghai China Key Laboratory of Intelligent Information Processing Fudan University Shanghai China School of Informatics and ELLIS University of Edinburgh United Kingdom

Retrieval-Augmented Generation (RAG) significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks. While existing research seeks to enhance RAG performance by retrieving higher-quality documents or designing RAG-specific LLMs, the internal mechanisms within LLMs that contribute to the effectiveness of RAG systems remain underexplored. In this paper, we aim to investigate these internal mechanisms within the popular Mixture-of-Expert (MoE)- based LLMs and demonstrate how to improve RAG by examining expert activations in these LLMs. Our controlled experiments reveal that several core groups of experts are primarily responsible for RAG-related behaviors. The activation of these core experts can signify the model's inclination towards external/internal knowledge and adjust its behavior. For instance, we identify core experts that can (1) indicate the sufficiency of the model's internal knowledge, (2) assess the quality of retrieved documents, and (3) enhance the model's ability to utilize context. Based on these findings, we propose several strategies to enhance RAG's efficiency and effectiveness through expert activation. Experimental results across various datasets and MoE-based LLMs show the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

PROV-IO+: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems

arXiv

引用

arXiv 2023年

作者： Han, Runzhou Zheng, Mai Byna, Suren Tang, Houjun Dong, Bin Dai, Dong Chen, Yong Kim, Dongkyun Hassoun, Joseph Thorsley, David Wolf, Matthew Department of Electrical and Computer Engineering Iowa State University United States Department of Computer Science and Engineering The Ohio State University United States Scientific Data Management Group Lawrence Berkeley National Laboratory United States Computer Science Department University of North Carolina Charlotte United States Systems Architecture Lab Samsung United States Samsung Advanced Institute of Technology Samsung Korea Republic of

Data provenance, or data lineage, describes the life cycle of data. In scientific workflows on HPC systems, scientists often seek diverse provenance (e.g., origins of data products, usage patterns of datasets). Unfortunately, existing provenance solutions cannot address the challenges due to their incompatible provenance models and/or system implementations. In this paper, we analyze four representative scientific workflows in collaboration with the domain scientists to identify concrete provenance needs. Based on the first-hand analysis, we propose a provenance framework called PROV-IO+, which includes an I/O-centric provenance model for describing scientific data and the associated I/O operations and environments precisely. Moreover, we build a prototype of PROV-IO+ to enable end-to-end provenance support on real HPC systems with little manual effort. The PROV-IO+ framework can support both containerized and non-containerized workflows on different HPC platforms with flexibility in selecting various classes of provenance. Our experiments with realistic workflows show that PROV-IO+ can address the provenance needs of the domain scientists effectively with reasonable performance (e.g., less than 3.5% tracking overhead for most experiments). Moreover, PROV-IO+ outperforms a state-of-the-art system (i.e., ProvLake) in our experiments. © 2023, CC BY-NC-SA.

关键词： Life cycle

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：