检索结果-内蒙古大学图书馆

An improved branching algorithm for the proper interval edge deletion problem

Frontiers of computer science 2022年第2期16卷 178-180页

作者： Wenjun LI Xiaojing TANG Yongjie YANG School of Computer and Communication Engineering Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on TransportationChangsha University of Science and TechnologyChangsha 410015China School of Computer Science and Engineering Central South UniversityChangsha 410083China

1 Introduction For a graph class G,the G-EDGE DELETION problem is to determine whether a given graph can be transformed into a graph in G by deleting at most k *** G-EDGE DELETION problem for a large body of graph cla... 详细信息

关键词： branching problem transformed

来源：评论

学校读者我要写书评

暂无评论

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret 41

Provably Efficient Exploration in Quantum Reinforcement Lear...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhong, Han Hu, Jiachen Xue, Yecheng Li, Tongyang Wang, Liwei Center for Data Science Peking University China School of Computer Science Peking University China Center on Frontiers of Computing Studies Peking University China National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China

While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is *** particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the exploration-exploitation *** this end, we propose a novel UCRL-style algorithm that takes advantage of quantum computing for tabular Markov decision processes (MDPs) with S states, A actions, and horizon H, and establish an O(poly(S, A, H, log T)) worst-case regret for it, where T is the number of ***, we extend our results to quantum RL with linear function approximation, which is capable of handling problems with large state ***, we develop a quantum algorithm based on value target regression (VTR) for linear mixture MDPs with d-dimensional linear representation and prove that it enjoys O(poly(d, H, log T)) *** algorithms are variants of UCRL/UCRL-VTR algorithms in classical RL, which also leverage a novel combination of lazy updating mechanisms and quantum estimation *** is the key to breaking the Ω(√T)-regret barrier in classical *** the best of our knowledge, this is the first work studying the online exploration in quantum RL with provable logarithmic worst-case regret. Copyright 2024 by the author(s)

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Resolution-Adaptive Representation Learning via Eliminating Abnormal Features for Cross-Resolution Person Re-Identification 14

Resolution-Adaptive Representation Learning via Eliminating ...

引用

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Lu, Xing Lai, Fengshan Cao, Zhixiang Xia, Daoxun Guizhou Normal University School of Big Data and Computer Science Guiyang China Guizhou Normal University Key Laboratory of Information and Computing Science Guizhou Province Guiyang China Guizhou Normal University Engineering Laboratory for Applied Technology of Big Data in Education Guiyang China

ISBN: (纸本)9798350356670

Cross-resolution person re-identification(CR-ReID) seeks to overcome the challenge of retrieving and matching specific person images across cameras with varying resolutions. Numerous existing studies utilize established CNNs and ViTs models to resize captured low-resolution (LR) images and align them with high-resolution (HR) image features. However, these methods overlook the potential feature connections between LR and HR images. Consequently, CNNs or ViTs tend to highlight outliers rather than the intended characteristics in LR image attention maps. In this work, we propose the abnormal feature elimination and reconfiguration transformer (ART) network, a novel network architecture, for robust cross-resolution person re-identification tasks. Our proposed method uses a resolution feature discriminator to learn resolution invariant features and outputs feature matrices of images with different resolutions. We utilize output feature matrices to model LR and HR image interactions through cross-resolution landmark agent attention. We aim to mitigate abnormal image features and prioritize the attention on the target person by learning representations from input images of various resolutions. Extensive evaluations on three real-world datasets confirm the excellent results of our approach. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Research on recognition algorithm for gesture page turning based on wireless sensing

引用

Intelligent and Converged Networks 2023年第1期4卷 15-27页

作者： Lin Tang Sumin Wang Meng Zhou Yinfan Ding Chao Wang Shengbo Wang Zhen Sun Jie Wu Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced CommunicationShanghai Institute for Advanced Communication and Data ScienceSchool of Communication and Information EngineeringShanghai UniversityShanghai 200444China School of Electronic Information Engineering Gannan University of Science and TechnologyGanzhou 341000China Affiliated High School of Peking University Beijing 100086China Peking University&National Engineering Laboratory for Big Data Analysis and Applications Beijing 100871China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122-6096USA

When a human body moves within the coverage range of Wi-Fi signals,the reflected Wi-Fi signals by the various parts of the human body change the propagation path,so analysis of the channel state data can achieve the perception of the human *** extracting the Channel State Information(CSI)related to human motion from the Wi-Fi signals and analyzing it with the introduced machine learning classification algorithm,the human motion in the spatial environment can be *** the basis of this theory,this paper proposed an algorithm of human behavior recognition based on CSI wireless sensing to realize deviceless and over-the-air slide *** algorithm collects the environmental information containing upward or downward wave in a conference room scene,uses the local outlier factor detection algorithm to segment the actions,and then the time domain features are extracted to train Support Vector Machine(SVM)and eXtreme Gradient Boosting(XGBoost)classification *** experimental results show that the average accuracy of the XGBoost module sensing slide flipping can reach 94%,and the SVM module can reach 89%,so the module could be extended to the field of smart classroom and significantly improve speech efficiency.

关键词： Wi-Fi signal Channel State Information(CSI) wireless sensing human behavior recognition

来源：评论

学校读者我要写书评

暂无评论

KnowLog: Knowledge Enhanced Pretrained Language Model for Log Understanding

KnowLog: Knowledge Enhanced Pretrained Language Model for Lo...

引用

International Conference on Software Engineering (ICSE)

作者： Lipeng Ma Weidong Yang Bo Xu Sihang Jiang Ben Fei Jiaqing Liang Mingjie Zhou Yanghua Xiao Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China *Zhuhai Fudan Innovation Institute Zhuhai China School of Computer Science and Technology Donghua University Shanghai China School of Data Science Fudan University Shanghai China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Logs as semi-structured text are rich in semantic information, making their comprehensive understanding crucial for automated log analysis. With the recent success of pretrained language models in natural language processing, many studies have leveraged these models to understand logs. Despite their successes, existing pretrained language models still suffer from three weaknesses. Firstly, these models fail to understand domain-specific terminol-ogy, especially abbreviations. Secondly, these models struggle to adequately capture the complete log context information. Thirdly, these models have difficulty in obtaining universal representations of different styles of the same logs. To address these challenges, we introduce KnowLog, a knowledge-enhanced pretrained language model for log understanding. Specifically, to solve the previous two challenges, we exploit abbreviations and natural language de-scriptions of logs from public documentation as local and global knowledge, respectively, and leverage this knowledge by designing novel pretraining tasks for enhancing the model. To solve the last challenge, we design a contrastive learning-based pretraining task to obtain universal representations. We evaluate KnowLog by fine-tuning it on six different log understanding tasks. Extensive experiments demonstrate that KnowLog significantly enhances log understanding and achieves state-of-the-art results compared to existing pretrained language models without knowledge enhancement. Moreover, we conduct additional experiments in transfer learning and low-resource scenarios, showcasing the substantial advantages of KnowLog. Our source code and detailed experimental data are available at https://***/LeaperOvO/KnowLog.

关键词： Knowledge engineering Flowcharts Source coding Transfer learning Semantics Documentation Natural language processing

来源：评论

学校读者我要写书评

暂无评论

SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning 27th

SecureCut: Federated Gradient Boosting Decision Trees with ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Bowen Zhang, Jian Li, Jie Wu, Chentao Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Yancheng Blockchain Research Institute Yancheng China Blockchain Advanced Research Center Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance and Web3 Shanghai China

ISBN: (纸本)9783031781681

In response to legislation, companies are now mandated to honor the right to be forgotten by erasing user data. Consequently, it has become imperative to enable data removal in Vertical Federated Learning (VFL), where multiple parties provide private features for model training. In VFL, data removal, i.e., machine unlearning, requires removing specific features across all samples, ensuring privacy in federated learning. To address this challenge, we propose SecureCut, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both instance unlearning and feature unlearning without the need for retraining from scratch. Leveraging a robust GBDT structure, we enable effective data deletion while reducing degradation of model performance. Extensive experimental results on popular datasets demonstrate that our method achieves superior model utility and forgetfulness compared to the state-of-the-art methods. To the best of our knowledge, this is the first work that investigates machine unlearning in VFL scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Channel assignment and power allocation for throughput improvement with PPO in B5G heterogeneous edge networks

引用

Digital Communications and Networks 2024年第1期10卷 109-116页

作者： Xiaoming He Yingchi Mao Yinqiu Liu Ping Ping Yan Hong Han Hu The College of Computer and Information Hohai UniversityNanjingChina The Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai UniversityNanjing China The School of Computer Science and Engineering Nanyang Technological UniversitySingapore The College of Textile and Clothing Engineering Soochow UniversitySuzhouChina The College of Internet of Things Nanjing University of Posts and TelecomurunicationsNanjingChina

In Beyond the Fifth Generation(B5G)heterogeneous edge networks,numerous users are multiplexed on a channel or served on the same frequency resource block,in which case the transmitter applies coding and the receiver uses interference ***,uncoordinated radio resource allocation can reduce system throughput and lead to user inequity,for this reason,in this paper,channel allocation and power allocation problems are formulated to maximize the system sum rate and minimum user achievable *** the construction model is non-convex and the response variables are high-dimensional,a distributed Deep Reinforcement Learning(DRL)framework called distributed Proximal Policy Optimization(PPO)is proposed to allocate or assign ***,several simulated agents are trained in a heterogeneous environment to find robust behaviors that perform well in channel assignment and power ***,agents in the collection stage slow down,which hinders the learning of other ***,a preemption strategy is further proposed in this paper to optimize the distributed PPO,form DP-PPO and successfully mitigate the straggler *** experimental results show that our mechanism named DP-PPO improves the performance over other DRL methods.

关键词： B5G Heterogeneous edge networks PPO Channel assignment Power allocation Throughput

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned Large Language Model for Visualization System: A Study on Self-Regulated Learning in Education

arXiv

引用

arXiv 2024年

作者： Gao, Lin Lu, Jing Shao, Zekai Lin, Ziyue Yue, Shengbin Ieong, Chiokit Sun, Yi Zauner, Rory James Wei, Zhongyu Chen, Siming The School of Data Science Fudan University China The Shanghai Key Laboratory of Data Science China The Faculty of Computer Science University of Vienna Vienna Austria

Large Language Models (LLMs) have shown great potential in intelligent visualization systems, especially for domain-specific applications. Integrating LLMs into visualization systems presents challenges, and we categorize these challenges into three alignments: domain problems with LLMs, visualization with LLMs, and interaction with LLMs. To achieve these alignments, we propose a framework and outline a workflow to guide the application of fine-tuned LLMs to enhance visual interactions for domain-specific tasks. These alignment challenges are critical in education because of the need for an intelligent visualization system to support beginners' self-regulated learning. Therefore, we apply the framework to education and introduce Tailor-Mind, an interactive visualization system designed to facilitate self-regulated learning for artificial intelligence beginners. Drawing on insights from a preliminary study, we identify self-regulated learning tasks and fine-tuning objectives to guide visualization design and tuning data construction. Our focus on aligning visualization with fine-tuned LLM makes Tailor-Mind more like a personalized tutor. Tailor-Mind also supports interactive recommendations to help beginners better achieve their learning goals. Model performance evaluations and user studies confirm that Tailor-Mind improves the self-regulated learning experience, effectively validating the proposed framework. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Native spaces and generalization of Wu functions

引用

science China Mathematics 2025年

作者： Yixuan Huang Zongmin Wu Shengxin Zhu Laboratory of Mathematics and Complex Systems (Ministry of Education of China) School of Mathematical Sciences Beijing Normal University Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai Center for Mathematical Sciences School of Big Data and Statistics Anhui University Advanced Institute of Natural Science Beijing Normal University Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science Beijing Normal-Hong Kong Baptist University

Wu functions are a class of positive definite compactly supported radial basis functions in terms of piecewise polynomials. They are similar to Wendland functions that came up shortly later and they still require further investigation. Here, we prove that the native space of a Wu function is a dense subspace of a Sobolev space and give an explicit characterization of the native spaces of Wu functions. In addition, three definitions of Wu functions are introduced and proven to be equivalent. Based on these new equivalent definitions and the so-called f-form, we can generalize the Wu functions for the even-dimensional spaces, while the original Wu functions are proven to have odd maximal possible dimensions on which they are positive definite. Such functions in even-dimensional spaces will be called the “missing Wu functions”. Furthermore, we can generalize the Wu functions to “fractional”-dimensional spaces. We call all these Wu functions the generalized Wu functions. The closed form of the generalized Wu functions is given in terms of hypergeometric functions. Finally, we prove that the Wu functions and the missing Wu functions can be written as linear combinations of the generalized Wendland functions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Speech Extraction for Multiple Target Speakers Under Meeting Scenarios

引用

Journal of shanghai Jiaotong University (science) 2024年 1-7页

作者： Zeng, Bang Suo, Hongbin Wan, Yulong Li, Ming School of Computer Science Wuhan University Wuhan430027 China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan Jiangsu215316 China Data & amp AI Engineering System OPPO Beijing100125 China

The common target speech separation directly estimates the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation (MTSS) model to simultaneously extract each speaker’s voice from the mixed speech rather than just optimally estimating the target source. Moreover, we propose a speaker diarization (SD) aware MTSS system (SD-MTSS). By exploiting the target speaker voice activity detection (TSVAD) and the estimated mask, our SD-MTSS model can extract the speech signal of each speaker concurrently in a conversational recording without additional enrollment audio in advance. Experimental results show that our MTSS model achieves improvements of 1.38 dB signal-to-distortion ratio (SDR), 1.34 dB scale-invariant signal-to-distortion ratio (SISDR), and 0.13 perceptual evaluation of speech quality (PESQ) over the baseline on the WSJ0-2mix-extr dataset, separately. The SD-MTSS system makes a 19.2% relative speaker dependent character error rate reduction on the Alimeeting dataset. © shanghai Jiao Tong University 2024.

关键词： Speech analysis

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：