检索结果-内蒙古大学图书馆

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhao, Qianyi Qu, Chen Chen, Cen Fan, Mingyuan Wang, Yanhao East China Normal University School of Data Science and Engineering Shanghai China University of Massachusetts Amherst College of Information & Computer Sciences AmherstMA United States

ISBN: (纸本)9798331515966

With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this problem still face two primary challenges. First, the huge number of parameters in large-scale PLMs leads to excessive communication and computational overhead. Second, the heterogeneity of data and tasks across clients poses a significant obstacle to achieving the desired fine-tuning performance. To address the above problems, we propose FedMCP, a novel parameter-efficient fine-tuning method with model-contrastive personalization for FL. Specifically, FedMCP adds two lightweight adapter modules, i.e., the global adapter and the private adapter, to the frozen PLMs within clients. In a communication round, each client sends only the global adapter to the server for federated aggregation. Furthermore, FedMCP introduces a model-contrastive regularization term between the two adapters. This, on the one hand, encourages the global adapter to assimilate universal knowledge and, on the other hand, the private adapter to capture client-specific knowledge. By leveraging both adapters, FedMCP can effectively provide fine-tuned personalized models tailored to individual clients. Extensive experiments on highly heterogeneous cross-task, cross-silo datasets show that FedMCP achieves substantial performance improvements over state-of-the-art FL fine-tuning approaches for PLMs. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

UNCERTAINTY-AWARE GRAPH-BASED HYPERSPECTRAL IMAGE CLASSIFICATION 12

UNCERTAINTY-AWARE GRAPH-BASED HYPERSPECTRAL IMAGE CLASSIFICA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Yu, Linlin Lou, Yifei Chen, Feng Department of Computer Science University of Texas Dallas United States Department of Mathematics School of Data Sciences and Society University of North Carolina Chapel Hill United States

Hyperspectral imaging (HSI) technology captures spectral information across a broad wavelength range, providing richer pixel features compared to traditional color images with only three channels. Although pixel classification in HSI has been extensively studied, especially using graph convolution neural networks (GCNs), quantifying epistemic and aleatoric uncertainties associated with the HSI classification (HSIC) results remains an unexplored area. These two uncertainties are effective for out-of-distribution (OOD) and misclassification detection, respectively. In this paper, we adapt two advanced uncertainty quantification models, evidential GCNs (EGCN) and graph posterior networks (GPN), designed for node classifications in graphs, into the realm of HSIC. We first reveal theoretically that a popular uncertainty cross-entropy (UCE) loss function is insufficient to produce good epistemic uncertainty when learning EGCNs. To mitigate the limitations, we propose two regularization terms. One leverages the inherent property of HSI data where each feature vector is a linear combination of the spectra signatures of the confounding materials, while the other is the total variation (TV) regularization to enforce the spatial smoothness of the evidence with edge-preserving. We demonstrate the effectiveness of the proposed regularization terms on both EGCN and GPN on three real-world HSIC datasets for OOD and misclassification detection tasks. The code is available at GitHub. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Security Challenges and Potential Solutions in Aerial-Terrestrial Wireless Networking

引用

IEEE Internet of Things Magazine 2023年第4期6卷 118-123页

作者： Sood, Keshav Nguyen, Dinh Duc Nha Qu, Youyang Cui, Lei Karmakar, Kallol Krishna Yu, Shui School of Information Technology Deakin University Australia Data61 Australia Shandong Computer Science Center National Supercomputer Center in Jinan China The University of Newcastle Australia University of Technology Sydney Australia

Integration of unmanned aerial vehicles (UAVs) with terrestrial networks form an aerial-terrestrial wireless networking concept. Particularly, the UAVs are composed of Internet of Things sensors (IoTs) and they also are typically known as flying IoTs. These are used to collect real-time data for diverse network's applications in order to make optimal network performance and secure management decisions. In this networking domain, cyber-attacks on UAVs sensors are rapidly increasing and the attacks on sensors inevitably raise the data sparsity issue, means the recorded data, by drones or UAVs, could be often incomplete and even sparse enough too. This impacts the performance eval-uation of this networking composed of flying and ground base stations. This paper explores the data sparsity issue in context of the integration of aerial-terrestrial wireless networks. Critical challenges and potential high-level solutions are also proposed to enhance the security and performance of networks. © 2018 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Comparative Model Evaluation of Lightweight Transformer-Based and CNN-Based Architechture for Degenerative Lumbar Spine Classification

Comparative Model Evaluation of Lightweight Transformer-Base...

引用

Advancement in data science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Jennifer Ardelia Limicia Wilbert Chandra Alexander Agung Santoso Gunawan Jeffrey Junior Tedjasulaksana Data Science Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Low back pain is a leading cause of disability globally, is often associated with degenerative lumbar spine conditions. Accurate diagnosis of these conditions is critical but challenging due to the subjective nature of MRI interpretation and the weak correlation between imaging findings and symptoms. Thus, the purpose of this study is to evaluate the performance of CNN-based architectures (VGG-16, EfficientNetB0, EfficientNetV2) and transformer-based architecture specifically Vision Transformers (ViT) in classifying lumbar spine conditions as normal, moderate, or severe. Using the RSNA 2024 Lumbar Spine Degenerative Classification dataset. The models are evaluated using the ROC-AUC and PRAUC as the performance metrics due to the dataset imbalance. Results indicate that EfficientNetB0 achieved the highest overall performance, with an average ROC-AUC of 0.784 and PR-AUC of 0.528, demonstrating strong adaptability to imbalanced datasets. EfficientNetV2 also performed competitively, while VGG-16 showed moderate effectiveness. The Vision Transformer (ViT), however, underperformed due to its reliance on larger datasets and challenges in capturing fine-grained spatial features. The findings highlight the potential of EfficientNet-based models for accurate and efficient lumbar spine diagnostics. This study underscores the potential of advanced deep learning approaches in improving diagnostic workflows for degenerative lumbar spine conditions.

关键词： computer vision Adaptation models Accuracy Magnetic resonance imaging Soft sensors Spine Transforms Transformers data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Parallel Segment Entanglement Swapping 1

Parallel Segment Entanglement Swapping

引用

1st International Conference on Quantum Communications, Networking, and Computing, QCNC 2024

作者： He, Binjie Loke, Seng W. Zhang, Dong College of Computer and Data Science Fuzhou University Fuzhou China School of Information Technology Deakin University Melbourne Australia Zhicheng College Fuzhou University Fuzhou China

ISBN: (纸本)9798350366778

In the noisy intermediate-scale quantum era, scientists are trying to improve the entanglement swapping success rate by researching anti-noise technology on the physical level, thereby obtaining a higher generation rate of long-distance entanglement. However, we may improve the generation rate from another perspective, which is studying an efficient entanglement swapping strategy. This paper analyzes the challenges faced by existing entanglement swapping strategies, including the node allocation principle, time synchronization, and processing of entanglement swapping failure. We present Parallel Segment Entanglement Swapping (PSES) to solve these problems. The core idea of PSES is to segment the path and perform parallel entanglement swapping between segments to improve the generation rate of long-distance entanglement. We construct a tree-like model as the carrier of PSES and propose heuristic algorithms called Layer Greedy and Segment Greedy to transform the path into a tree-like model. Moreover, we realize the time synchronization and design the on-demand retransmission mechanism to process entanglement swapping failure. The experiments show that PSES performs superiorly to other entanglement swapping strategies, and the on-demand retransmission mechanism can reduce the average entanglement swapping time by 80% and the average entanglement consumption by 80%. © 2024 IEEE.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Subgraph Extraction: Methods, Applications and Challenges 49th

Machine Learning for Subgraph Extraction: Methods, Applicati...

引用

49th International Conference on Very Large data Bases, VLDB 2023

作者： Yow, Kai Siong Liao, Ningyi Luo, Siqiang Cheng, Reynold School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computer Science Guangdong-Hong Kong-Macau Joint Laboratory HKU Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong

Subgraphs are obtained by extracting a subset of vertices and a subset of edges from the associated original graphs, and many graph properties are known to be inherited by subgraphs. Subgraphs can be applied in many areas such as social networks, recommender systems, biochemistry and fraud discovery. Researchers from various communities have paid a great deal of attention to investigate numerous subgraph problems, by proposing algorithms that mainly extract important structures of a given graph. There are however some limitations that should be addressed, with regard to the efficiency, effectiveness and scalability of these traditional algorithms. As a consequence, machine learning techniques—one of the most latest trends—have recently been employed in the database community to address various subgraph problems considering that they have been shown to be beneficial in dealing with graphrelated problems. We discuss learning-based approaches for four well known subgraph problems in this tutorial, namely subgraph isomorphism, maximum common subgraph, community detection and community search problems. We give a general description of each proposed model, and analyse its design and performance. To allow further investigations on relevant subgraph problems, we suggest some potential future directions in this area. We believe that this work can be used as one of the primary resources, for researchers who intend to develop learning models in solving problems that are closely related to subgraphs. © 2023, VLDB Endowment. 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

Adaptive Operator Selection for Meta-Heuristics: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Pei, Jiyuan Mei, Yi Liu, Jialin Zhang, Mengjie Yao, Xin Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington New Zealand Lingnan University School of Data Science Hong Kong Hong Kong

Appropriate selection of search operators plays a critical role in meta-heuristic algorithm design. Adaptive selection of suitable operators to the characteristics of different optimization stages is an important task that owns promising potential to improve the performance of a meta-heuristic algorithm. A variety of adaptive operator selection methods have been proposed in last decades, from the machine learning and optimization communities. However, the existing studies have not been systematically reviewed so far. To fill the gap, this paper provides a comprehensive survey of adaptive operator selection for meta-heuristics. According to the information required for selection, adaptive operator selection methods are classified into two categories: (i) stateless methods and (ii) state-based methods. Each category is further summarized into several key components. The strategies of each component belonging to the two categories are reviewed respectively. The motivation, strengths and weaknesses of the proposed strategies are also discussed. Furthermore, studied meta-heuristics and optimization problems in the literature are summarized. The effects from the difference of meta-heuristics and problems to the specific design of methods are discussed, together with the guidance of selecting the suitable method in different application scenarios. At the end, emerging challenges that could guide further research are discussed. © 2020 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Management with Graphic Deep Reinforcement Learning in Space-Air-Ground Integrated Networks

Dynamic Resource Management with Graphic Deep Reinforcement ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Cai, Yue Cheng, Peng Chen, Zhuo Xiang, Wei Vucetic, Branka Li, Yonghui The University of Sydney School of Electrical and Information Engineering Australia La Trobe University Department of Computer Science and Information Technology Australia Csiro Data61 Australia

ISBN: (纸本)9798350351255

Space-Air-Ground integrated network (SAGIN) is a crucial component of the 6G, enabling global and seamless communication coverage. An efficient task offloading and resource allocation scheme is key in SAGIN to maximize resource utilization efficiency, meeting the stringent quality of service (QoS) requirements for different service types. In this paper, we introduce a dynamic SAGIN model featuring diverse antenna configurations, two timescale types, different channel models for each segment, and dual service types. We formulate a problem of sequential decision-making task offloading and resource allocation. Our proposed solution is an innovative online approach referred to as graphic deep reinforcement learning (GDRL). This approach utilizes a graph neural network (GNN)-based feature extraction network to identify the inherent dependencies within the graphical structure of the states. Simulation results validate that our proposed GDRL significantly outperforms state-of-the-art deep reinforcement learning (DRL) approaches by achieving the highest reward and lowest overall latency. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Supervised Satellite Image Retrieval using Defined Patterned with ASMC 2

Supervised Satellite Image Retrieval using Defined Patterned...

引用

2nd Edition of IEEE Delhi Section Owned Conference, DELCON 2023

作者： Gaikwad, Rohini Siddiqui, Rizwana Sies Graduate School of Technology Artificial Intelligence & Data Science Navi Mumbai India Sies Graduate School of Technology Computer Engineering Navi Mumbai India

ISBN: (纸本)9798350322064

It is suggested to use remotely sensed image retrieval with query-by-example approach. This often entails using query techniques that permit descriptive semantics, queries that incorporate user feedback, machine learning-capable systems, and systems that can gauge user satisfaction. This study uses the Advanced Split and Merge Clustering approach to extract features from the textures of similar grayscale images and the spectral distribution using two-dimensional Gabor functions. The resulting pattern will be the concatenation of texture features and Spectral Distribution (SD). Modified Earth Mover's Distance (EMD) is used to limit how much of each vector can be predefined in pieces. EMD technique for establishing center correspondence between the patterns uses interactive search. © 2023 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

MCITEBENCH: A Benchmark for Multimodal Citation Text Generation in MLLMs

arXiv

引用

arXiv 2025年

作者： Hu, Caiyu Zhang, Yikai Zhu, Tinghui Ye, Yiwei Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Computer Engineering and Science Shanghai University China

Multimodal Large Language Models (MLLMs) have advanced in integrating diverse modalities but frequently suffer from hallucination. A promising solution to mitigate this issue is to generate text with citations, providing a transparent chain for verification. However, existing work primarily focuses on generating citations for text-only content, overlooking the challenges and opportunities of multimodal contexts. To address this gap, we introduce MCITEBENCH, the first benchmark designed to evaluate and analyze the multimodal citation text generation ability of MLLMs. Our benchmark comprises data derived from academic papers and review-rebuttal interactions, featuring diverse information sources and multimodal content. We comprehensively evaluate models from multiple dimensions, including citation quality, source reliability, and answer accuracy. Through extensive experiments, we observe that MLLMs struggle with multimodal citation text generation. We also conduct deep analyses of models’ performance, revealing that the bottleneck lies in attributing the correct sources rather than understanding the multimodal content. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

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：