检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ma, Tianmi Du, Jiawei Huang, Wenxin Wang, Wenjie Xie, Liang Zhong, Xian Zhou, Joey Tianyi Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computing National University of Singapore Singapore School of Science Wuhan University of Technology China

Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks. However, their ability to generalize to dynamic, unseen tasks, particularly in numerical reasoning, remains a challenge. Existing benchmarks mainly evaluate LLMs on problems with predefined optimal solutions, which may not align with real-world scenarios where clear answers are absent. To bridge this gap, we design the Agent Trading Arena, a virtual numerical game simulating complex economic systems through zero-sum games, where agents invest in stock portfolios. Our experiments reveal that LLMs, including GPT-4o, struggle with algebraic reasoning when dealing with plain-text stock data, often focusing on local details rather than global trends. In contrast, LLMs perform significantly better with geometric reasoning when presented with visual data, such as scatter plots or K-line charts, suggesting that visual representations enhance numerical reasoning. This capability is further improved by incorporating the reflection module, which aids in the analysis and interpretation of complex data. We validate our findings on NASDAQ STOCK dataset, where LLMs demonstrate stronger reasoning with visual data compared to text. Our code and data are publicly available at https://***/wekjsdvnm/***. © 2025, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Collaboration for Vehicular Task Offloading Using Federated Deep Reinforcement Learning

引用

IEEE Transactions on Mobile computing 2025年

作者： Chen, Xing Xiao, Bohuai Lin, Xinyu Chen, Zheyi Min, Geyong Fuzhou University College of Computer and Data Science Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Mobile Edge computing (MEC) distributes resources such as computing, storage, and bandwidth to the side close to users, which can provide low-latency services to in-vehicle users, thus promising a more efficient and safer driving environment. However, due to the dynamic scale of vehicle and the variability of resource requirements, it is a significant challenge to quickly obtain effective task offloading in large-scale vehicle scenarios. The existing studies generally adopt the centralized decision-making method, with long decision-making time and high computational overhead, which cannot effectively achieve good offloading decisions in large-scale scenarios. To address these problems, we propose a Multi-agent Collaborative Method for vehicular task offloading using Federated Deep Reinforcement Learning called MCM-FDRL. First, each vehicle as an agent, independently makes offloading decisions based on local information. Next, the offloading decision model of each vehicle is obtained through federated reinforcement learning training. At runtime, an effective vehicle offloading plan can be gradually developed through multi-agent collaboration. Using two real-world datasets, experiments show that the MCM-FDRL has good adaptability and scalability. Moreover, compared to the state-of-the-art methods, the task's average response time of the MCM-FDRL is reduced by 9.75%-64.90%, respectively. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

PEFN: A Patches Enhancement and Hierarchical Fusion Network for Robust Vehicle Re-Identification

引用

IEEE Internet of Things Journal 2025年

作者： He, Wenying Wang, Feiyu Bai, Yude Xiong, Neal N. Xu, Guangquan Guo, Fei Hebei University of Technology School of Artificial Intelligence Tianjin300401 China Hebei University of Technology Hebei Province Key Laboratory of Big Data Calculation Tianjin300130 China Tiangong University School of Software Tianjin300387 China Northeastern State University Department of Mathematics and Computer Science TahlequahOK74464 United States Tianjin300350 China Central South University School of Computer Science and Engineering Changsha410083 China

Vehicle Re-Identification (Re-ID), which is a significant application in the Internet of Things, aims to accurately retrieve the remaining images of a given vehicle across different cameras views. The improvement in vehicle Re-ID performance largely stems from better addressing the issues of inter-class similarity and intra-class variance. Existing methods, relying solely on max or average pooling after using attention modules, fail to obtain significantly complete and pure global and local features, and neglect the false guidance that some unique individual information on images bring to re-identification. Moreover, models combining global and local features have shown good results in vehicle Re-ID, but these successes neglect the interaction between features across different convolutional layers, resulting in the loss of crucial details for vehicle Re-ID. To tackle these issues, we introduce a Patches Enhancement and hierarchical Fusion Network (PEFN) based on a multi-branch architecture, divided into a Global and Local Attention Supplement (GLAS) branch, and an Enhanced Hierarchical feature fusion (EnHi) branch. The GLAS branch, through the Identity-related Feature Remodeling (IDFR) module’s staged supplementation of spatial and channel features, has achieved the enhancement of both global and local features and effectively mitigated the negative impacts of individual information. The EnHi branch enhances the robustness of feature representation by interacting hierarchical features. Extensive experiments on two large-scale vehicle re-identification datasets demonstrate that our PEFN method outperforms state-of-the-art vehicle re-identification approaches. Specifically, without utilizing extra data and re-ranking, our model achieves 85.15% mAP on the VeRi776 dataset. © 2014 IEEE.

关键词： Reamers

来源：评论

学校读者我要写书评

暂无评论

A Bi-selection Method Based on Consistent Matrix for Large-Scale datasets

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Quan, Jinsheng Qiao, Fengcai Yang, Tian Shen, Shuo Qian, Yuhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Institute of Interdisciplinary Studies Changsha410081 China National University of Defense Technology College of Advanced Interdisciplinary Studies Changsha410081 China Shanxi University Institute of Big Data Science and Industry Taiyuan030006 China

Biselection (feature and sample selection) enhances the efficiency and accuracy of machine learning models when handling large-scale data. Fuzzy rough sets, an uncertainty mathematics model known for its excellent interpretability, are widely used in machine learning, particularly for feature selection. While the consistent matrix has significantly improved the computational efficiency and scalability of feature selection, like most fuzzy rough set-based methods, it focuses only on feature selection and seldom incorporates sample selection. This feature-centric approach can limit classification performance, particularly in noisy and large-scale datasets where both features and samples require judicious selection. To overcome these limitations, this article explores the integration of sample selection with feature selection. First, we introduce a β-consistent granulation method to generate more accurate and concise fuzzy information granules, reducing the impact of noisy samples. In addition, a novel membership function is employed to distinguish noise while simultaneously evaluating both features and samples. As a result, a biselection algorithm with linear computation complexity is proposed to select high-quality features and samples. Numerical experiments demonstrate that, compared to eleven representative algorithms, our proposed method achieves an average accuracy improvement of 9.66% and a 933-fold increase in efficiency. © 2025 IEEE.

关键词： Biselection consistent matrix (CM) fuzzy sets granular computing rough sets

来源：评论

学校读者我要写书评

暂无评论

A Fusion Tuning Method for Named Entity Recognition 12th

A Fusion Tuning Method for Named Entity Recognition

引用

12th CCF Conference on bigdata, bigdata 2024

作者： Wang, Jitian Chen, Yanping Zou, Anqi Qin, Yongbin Huang, Ruizhang Text Computing and Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang China College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9789819610235

In named entity recognition, the main methods for constructing deep neural networks are fine-tuning and prompt tuning. Fine-tuning is a commonly used paradigm to optimize neural networks by using task-specific objective functions to make them more adapted to solve downstream tasks. In which pre-trained language models are used as external resources to provide contextual representations. Prompt tuning is a recent paradigm in which the downstream tasks are reformulated to look more like those solved during the original PLM training with the help of a textual prompt. It is effective to utilize potential knowledge of PLMs. In this paper, we propose the fusion approach, which sufficiently fuses the semantics obtained by extracting fine-tuning and prompt-tuning. In our approach, the model makes decisions based on the information obtained from the reconstructive fusion of the fine-tuned semantics and the semantics of the pre-trained language model. The representation obtained by fine-tuning and the representation obtained by prompt tuning are reconstructed into a multidimensional semantics using a gate fusion module (GFM). In particularly, our model has two gate components, one gate to extract the semantics of fine-tuning and the other gate to extract the semantics of prompt tuning, and finally the reconstructed semantic representation is obtained. This takes full advantage of the potential knowledge of PLM. Our model is evaluated on the CONLL2003, ACE2005 and GENIA corpora. It achieves performance close to the state-of-the-art in F1 scores. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

QoS-Based Beamforming and Compression Design for Cooperative Cellular Networks via Lagrangian Duality

引用

IEEE Transactions on Signal Processing 2025年

作者： Fan, Xilai Liu, Ya-Feng Liu, Liang Chang, Tsung-Hui Chinese Academy of Sciences State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Beijing100190 China The Hong Kong Polytechnic University Department of Electronic and Information Engineering Hong Kong Hong Kong The Chinese University of HongKong School of Science and Engineering Shenzhen Shenzhen China Shenzhen Research Institute of Big Data China

This paper considers the quality-of-service (QoS)-based joint beamforming and compression design problem in the downlink cooperative cellular network, where multiple relay-like base stations (BSs), connected to the central processor via ratelimited fronthaul links, cooperatively transmit messages to the users. The problem of interest is formulated as the minimization of the total transmit power of the BSs, subject to all users' signal-to-interference-plus-noise ratio (SINR) constraints and all BSs' fronthaul rate constraints. In this paper, we first show that there is no duality gap between the considered joint optimization problem and its Lagrangian dual by showing the tightness of its semidefinite relaxation (SDR). Then, we propose an efficient algorithm based on the above duality result for solving the considered problem. The proposed algorithm judiciously exploits the special structure of an enhanced Karush-Kuhn-Tucker (KKT) conditions of the considered problem and approaches the solution that satisfies the enhanced KKT conditions via two fixed point iterations. Two key features of the proposed algorithm are: (1) it is able to detect whether the considered problem is feasible or not and find its globally optimal solution when it is feasible;(2) it is highly efficient because both of the fixed point iterations in the proposed algorithm are linearly convergent and function evaluations in the fixed point iterations are computationally cheap. Numerical results show the global optimality and efficiency of the proposed algorithm. © 1991-2012 IEEE.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

CMCache: An Adaptive Cross-Level data Placement Method for Multi-Level Cache

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Zeng, Zhaoyang Tan, Yujuan Ma, Zhulin Li, Jiali Zhao, Sanle Liu, Duo Chen, Xianzhang Ren, Ao Chongqing University College of Computer Science Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing400044 China Chongqing Universityof Posts and Telecommunications College of Software Engineering China Chongqing University College of Big Data and Software Engineering Chongqing China

Multi-level cache systems enhance I/O performance by optimizing data placement across various cache levels from a global perspective. However, existing methods often struggle to place data at the optimal cache level promptly due to their reliance on historical access patterns and inflexible placement strategies. These methods face two main challenges: (1) For already cached data with sufficient access history, existing approaches only optimize movement between adjacent cache levels, potentially delaying data arrival at its globally optimal cache level and leading to unnecessary bandwidth consumption and increased latency. (2) For newly entered data without access history, current methods cannot accurately predict their future hotness and simply place them at a fixed cache level (i.e. first or last level), overlooking future accesses of new data and potentially resulting in high cache miss rates or cache pollution. To address these issues, we propose CMCache, an adaptive cross-level data placement method for multi-level cache. CMCache applies distinct placement strategies for cached and new data to reach the optimal level timely, considering their different characteristics. It also logically divides cache space into two sections to manage cached and new data separately, dynamically adjusting section sizes based on access patterns. This approach significantly improves data placement efficiency, achieving up to an 89% reduction in miss rates and a 79% decrease in average response times compared to existing methods. © 2025 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

NOBGP: A Novel Optimized Balanced Graph Partitioning Algorithm 19th

NOBGP: A Novel Optimized Balanced Graph Partitioning Algorit...

引用

19th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2024

作者： Chen, Jiebin Hu, Ziqiang Ye, Renjie Zhang, Qishan Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Xianda College of Economics and Humanities Shanghai International Studies University Shanghai China

ISBN: (纸本)9789819623723

Large-scale graphs have become prevalent with the advent of the big data era. Distributed graph computing systems are commonly used for processing and analyzing large-scale graphs, with graph partitioning being a key prerequisite for their efficient computation. Graph partitioning aims to balance the load across partitions while minimizing the number of cut-edges. Moreover, it should achieve high efficiency and scalability. However, the existing popular graph partitioning algorithms do not fully take into account the internal topology of real-world graphs, which affects the final partition quality and convergence. Meanwhile, they easily fall into the local optimum due to partition load constraints. This paper introduces a Novel Optimized Balanced Graph Partitioning algorithm (NOBGP). First, we propose an initialization strategy based on label propagation of core vertices to achieve initial partitions with good locality and accelerate convergence. Second, we optimize the label propagation process to ensure balanced partitions and propose a probability-based disruption strategy to avoid the local optimum. We implement NOBGP on the distributed graph computing framework GraphX. Extensive experimental results on real-world graphs show that the proposed algorithm is scalable and performs better than the existing algorithms. We also run PageRank and Louvain applications using the graph partitioning results to demonstrate the efficiency of our algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Liang, Hanzhe Zhou, Jie Chen, Xuanxin Dai, Tao Wang, Jinbao Gao, Can College of Computer Science and Software Engineering Shenzhen University China Shenzhen Audencia Financial Technology Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Faculty of Education Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgements to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Semantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem’s causal logic. Copyright © 2025, The Authors. All rights reserved.

关键词： Fences

来源：评论

学校读者我要写书评

暂无评论

Discovering optimal Markov blanket for high-dimensional streaming features

引用

Information Sciences 2025年 716卷

作者： Khan, Waqar Brekhna, Brekhna Xie, Yajun Zada, Muhammad Sadiq Hassan Shah, Rasool Zheng, Yifan School of Big Data Fuzhou University of International Studies and Trade Fujian Fuzhou350202 China Department of Computer Science Shaheed Benazir Bhutto Women University Peshawar00384 Pakistan Key Laboratory of Data Science and Intelligent Computing Fuzhou University of International Studies and Trade Fujian Fuzhou350202 China College of Computing and Engineering University of Derby DerbyDE22 1GB United Kingdom Department of Computer Science and Mathematics Lebanese American University Beirut13-5053 Lebanon

Conducting knowledge discovery on high-dimensional streaming features requires an online causal feature selection process that can significantly reduce the complexity of real-world feature spaces and enhance the learning process. This is achieved by mining online causal features to construct a Markov blanket (MB) for the class label, select highly relevant subsets, and minimize the numbers of irrelevant and redundant features within contained the streaming feature space. However, the prevailing MB algorithms (e.g., offline and online methods) often fall short in terms of discerning the causal relationship between a class label and the selected features, rendering them ineffective and inefficient for addressing high-dimensional streaming feature spaces. We propose a novel algorithm named Discovering Optimal - Markov blanket for high-dimensional Streaming Features (DO-MBSF) to address these limitations, and this approach is tailored to optimally learn an MB online. First, DO-MBSF dynamically learns the parents (Ps), children (Cs), and spouses of class labels, thereby distinguishing PC relationships from spouses and Ps from Cs during the MB learning procedure. Second, learning relevant PC and spousal relationships and accurately distinguishing them enables a balance to be struck between prediction accuracy and computational efficiency, ensuring a comprehensive online causal feature selection approach. An extensive experimental validation highlights the superiority of the DO-MBSF algorithm in terms of accuracy and efficiency. By identifying powerfully relevant PC and spousal relationships and optimizing the tradeoff between accuracy and efficiency, DO-MBSF is a promising solution for performing online causal feature selection in high-dimensional streaming feature spaces. The code has been released on https://***/vickykhan89/DO-MBSF. © 2025 Elsevier Inc.

关键词： Markov processes

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：