检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Lingbing Bo, Zhongpu Chen, Zhuo Zhang, Yichi Chen, Jiaoyan Lan, Yarong Sun, Mengshu Zhang, Zhiqiang Luo, Yangyifei Li, Qian Zhang, Qiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China Department of Computer Science The University of Manchester United Kingdom School of Computer Science and Engineering Beihang University China School of Computer Science Beijing University of Posts and Telecommunications China School of Software Technology Zhejiang University China

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Education in Smart Cities: Challenges And Solution 9

Smart Education in Smart Cities: Challenges And Solution

引用

9th IEEE International Smart Cities Conference, ISC2 2023

作者： Badshah, Afzal Nasralla, Moustafa M. Jalal, Ateeqa Farman, Haleem Hamdard University Islamabad Campus Department of Computing Islamabad Pakistan College of Engineering Prince Sultan University Smart Systems Engineering Lab Department of Communications and Engineering Riyadh Saudi Arabia University of Science and Technology Department of Computer Science Bannu Pakistan

ISBN: (纸本)9798350397758

Traditional education faces many challenges. Integrating recent technologies (e.g., Artificial Intelligence (AI), Internet of Things (IoT), 5G, etc) into the education system, known as smart education, offers promising solutions. However, the integration of innovative solutions into the traditional system remains limited. The limitations, revealed during the recent COVID-19 pandemic, have now become imperative. This study addresses problems within the traditional system and proposes innovative solutions like smart pedagogy, assessment, classroom, and administration. It explores the shift to smart education and the associated challenges, including computational and social resistance. Innovative education yields concrete benefits, enhancing learner engagement, motivation, attendance, and learning outcomes. Embracing innovative technologies holds the potential to make education more effective and efficient in meeting the evolving needs of learners. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction

Advanced Zero-Shot Text-to-Speech for Background Removal and...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Leying Zhang, Wangyou Chen, Zhengyang Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Although it may be necessary to remove background to ensure speech clarity, preserving the background is sometimes crucial to maintaining the contextual integrity of the speech. Despite recent advancements in zero-shot Text-to-Speech technologies, current systems often struggle with speech prompts containing backgrounds. To address these challenges, we propose a Controllable Masked Speech Prediction strategy coupled with a dual-speaker encoder, utilizing a task-related control signal to guide the prediction of dual background removal and preservation targets. Experimental results demonstrate that our approach enables precise control over the removal or preservation of background across various acoustic conditions and exhibits strong generalization capabilities in unseen scenarios. © 2025 IEEE.

关键词： background preservation background removal flow-matching text-to-speech

来源：评论

学校读者我要写书评

暂无评论

Iterative Noisy-Target Approach: Speech Enhancement Without Clean Speech 18th

Iterative Noisy-Target Approach: Speech Enhancement Without ...

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Zhang, Yifan Jiang, Wenbin Zhuo, Qing Yu, Kai MoE Key Lab of Artificial Intelligence X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Communication Engineering Hangzhou Dianzi University Hangzhou China Department of Automation Tsinghua University Beijing China

ISBN: (纸本)9789819706006

Traditional Deep Neural Network based speech enhancement usually requires clean speech as the target of training. However, limited access to ideal clean speech hinders its practical use. Meanwhile, existing self-supervised or unsupervised methods face both unsatisfactory performance and impractical source demand (e.g., various kinds of noises added to the same clean speech). Hence, there’s a significant need to either release the restriction of training data or improve the performance. In this paper, we propose a training strategy that only requires noisy speech and noise waveform. It primarily consists of two phases: 1) With a pair of input and target constructed by adding noise to noisy speech itself for the training of DNN, the first round of training uses noisier speech (noise added to noisy speech) and noisy speech 2) For the following training, using the model trained last time to refine the noisy speech, construct new noisier-noisy pairs for next turn of training. Moreover, to accelerate the process, we apply the iteration into epochs. To evaluate the efficiency, we utilized a dataset including 10 types of real-world noises and made a comparison with two classic supervised and unsupervised methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Technological challenges faced by Digital Influencers in Brazil: perceptions of women from generations X, Y and Z 11

Technological challenges faced by Digital Influencers in Bra...

引用

11th International Conference on Information Technology and Quantitative Management, ITQM 2024

作者： Santos, Maíra Rocha de Sousa, Thainara Silva Mariano, Ari Melo Department of Administration University of Brasília Brazil Department of Production Engineering University of Brasília Brazil Department of Computer Science University of Brasilia Brazil DataLab-Data Lab University of Brasilia Brazil

This exploratory qualitative study sought to identify the main technological gaps faced by digital influencers from generations X, Y, and Z. Using interviews with open questions, perceptions of nine Brazilian digital influencers from different areas and age groups were collected. The interviews, with an average duration of 40 minutes, addressed two blocks: the influencers' profile and perception of the technologies used. The content analysis through a Similitude Tree created by the Iramuteq software revealed common gaps between generations, such as adaptation to new platforms, emotional control, search for engagement, and constant updating. Understanding these nuances across generations allows for tailored solutions to minimize technological challenges and promote digital inclusion and professional success for these women. Future studies should explore creating a structural equation model to test the standard dimensions found. © 2024 The Authors.

关键词： Brazil Digital Influencers Generations X, Y and Z Technology Tree of Similitude

来源：评论

学校读者我要写书评

暂无评论

Hybrid Chaotic Salp Swarm with Crossover Algorithm for Underground Wireless Sensor Networks

引用

computers, Materials & Continua 2022年第8期72卷 2963-2980页

作者： Mariem Ayedi Walaa H.ElAshmawi Esraa Eldesouky First Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia MEDIATRON Lab. SUP’COMCarthage UniversityTunis2083Tunisia Department of Computer Science Faculty of Computers and InformaticsSuez Canal UniversityIsmailia41522Egypt Faculty of Computer Science Misr International UniversityCairoEgypt

Resource management in Underground Wireless Sensor Networks(UWSNs)is one of the pillars to extend the network *** intriguing design goal for such networks is to achieve balanced energy and spectral resource *** paper focuses on optimizing the resource efficiency in UWSNs where underground relay nodes amplify and forward sensed data,received from the buried source nodes through a lossy soil medium,to the aboveground base station.A new algorithm called the Hybrid Chaotic Salp Swarm and Crossover(HCSSC)algorithm is proposed to obtain the optimal source and relay transmission powers to maximize the network resource *** proposed algorithm improves the standard Salp Swarm Algorithm(SSA)by considering a chaotic map to initialize the population along with performing the crossover technique in the position updates of *** experimental results,the HCSSC algorithm proves its outstanding superiority to the standard SSA for resource efficiency ***,the network’s lifetime is ***,the proposed algorithm achieves an improvement performance of 23.6%and 20.4%for the resource efficiency and average remaining relay battery per transmission,***,simulation results demonstrate that the HCSSC algorithm proves its efficacy in the case of both equal and different node battery capacities.

关键词： Underground wireless sensor networks resource efficiency chaotic theory crossover algorithm salp swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

A disk I/O optimized system for concurrent graph processing jobs

引用

Frontiers of computer science 2024年第3期18卷 13-29页

作者： Xianghao XU Fang WANG Hong JIANG Yongli CHENG Dan FENG Peng FANG School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China Department of Computer Science&Engineering University of Texas at ArlingtonArlingtonTX 76019USA College of Computer and Data Science Fuzhou UniversityFuzhou 350108China Zhejiang Lab Hangzhou 311121China

In order to analyze and process the large graphs with high cost efficiency,researchers have developed a number of out-of-core graph processing systems in recent years based on just one commodity *** the other hand,with the rapidly growing need of analyzing graphs in the real-world,graph processing systems have to efficiently handle massive concurrent graph processing(CGP)***,due to the inherent design for single graph processing job,existing out-of-core graph processing systems usually incur unnecessary data accesses and severe competition of I/O bandwidth when handling the CGP *** this paper,we propose GraphCP,a disk I/O optimized out-of-core graph processing system that efficiently supports the processing of CGP *** proposes a benefit-aware sharing execution model to share the I/O access and processing of graph data among the CGP jobs and adaptively schedule the graph data loading based on the states of vertices,which efficiently overcomes above challenges faced by existing out-of-core graph processing ***,GraphCP adopts a dependency-based future-vertex updating model so as to reduce disk I/Os in the future *** addition,GraphCP organizes the graph data with a Source-Sorted Sub-Block graph representation for better processing capacity and I/O access *** evaluation results show that GraphCP is 20.5×and 8.9×faster than two out-of-core graph processing systems GridGraph and GraphZ,and 3.5×and 1.7×faster than two state-of-art concurrent graph processing systems Seraph and GraphSO.

关键词： graph processing disk I/O concurrent jobs

来源：评论

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection 42

FedMoS: Taming Client Drift in Federated Learning with Doubl...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wang, Xiong Chen, Yuxin Li, Yuqing Liao, Xiaofei Jin, Hai Li, Bo Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Wuhan China Wuhan University School of Cyber Science and Engineering Wuhan China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients' selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal O(T - 2/3) convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques. © 2023 IEEE.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning-Based YOLOv5 Detector for Efficient labor Protection Products Detection 15th

Incremental Learning-Based YOLOv5 Detector for Efficient Lab...

引用

15th International Conference on computer science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2023

作者： Du, Liangao Fang, Yang Deng, Xin Ouyang, Weihua Li, Yan Li, Yahui DEVC Lab Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Electrical and Computer Engineering Inha University Incheon22212 Korea Republic of Editorial Office of Computer Science Chongqing401121 China

ISBN: (纸本)9789819724468

In recent years, the accident rates remain high in the construction industry, and the construction safety is a matter of great concern worldwide. An intelligent and efficient incremental detector that can accurately detect whether the workers properly wear labor protection products, such as Safety helmet, safety belt, reflective clothing, is crucial for construction safety. Currently, the most advanced incremental detectors mostly adopt external fixed region proposal methods based on knowledge distillation, which require a lot of time and cost. Due to the lack of annotations for old categories and region proposal information in single-stage detectors, the detectors usually identify old category targets as background, leading to catastrophic forgetting. To address the above problems, this paper proposes a data label merging algorithm, which uses the detection results of the old model and existing data labels to generate merged labels for training, which compensates for the missing annotations of old category targets in the new dataset and mitigates catastrophic forgetting. At the same time, a recent mean-based exemplar selection algorithm is proposed to select representative samples stored in the old dataset, and this representative sample set will be used for model training to help the model resist forgetting. This method has been implemented in a single-stage detection framework, and its effectiveness has been verified on the LPAD (labor Protection Appliance-Dataset) dataset. Our proposed method improves the average precision score (mAP) of old categories and total categories detections by 6.9% and 6.0% respectively compared with the current state-of-the-art method. The merged labels and representative samples obtained from the proposed method effectively alleviate the forgetting problem. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Construction industry

来源：评论

学校读者我要写书评

暂无评论

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

引用

Journal of Machine Learning Research 2023年第1期24卷 1-11页

作者： Hedström, Anna Weber, Leander Bareeva, Dilyara Krakowczyk, Daniel Motzkus, Franz Samek, Wojciech Lapuschkin, Sebastian Höhne, Marina M.-C. Understandable Machine Intelligence Lab TU Berlin Berlin10587 Germany Department of Electrical Engineering and Computer Science TU Berlin Berlin10587 Germany Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin10587 Germany Department of Computer Science University of Potsdam Potsdam14476 Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. Until now, no tool with focus on XAI evaluation exists that exhaustively and speedily allows researchers to evaluate the performance of explanations of neural network predictions. To increase transparency and reproducibility in the field, we therefore built Quantus—a comprehensive, evaluation toolkit in Python that includes a growing, wellorganised collection of evaluation metrics and tutorials for evaluating explainable methods. The toolkit has been thoroughly tested and is available under an open-source license on PyPi (or on https://***/understandable-machine-intelligence-lab/Quantus/). © 2023 Anna Hedström, Leander Weber, Dilyara Bareeva, Daniel Krakowczyk, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, and Marina M.-C. Höhne.

关键词： Open systems

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：