检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Wael Alghamdi Hsiang Hsu Haewon Jeong Hao Wang P. Winston Michalak Shahab Asoodeh Flavio P. Calmon John A. Paulson School of Engineering and Applied Sciences Harvard University Department of Computing and Software McMaster University

ISBN: (纸本)9781713871088

We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks. We formulate this problem in terms of "projecting" a pre-trained (and potentially unfair) classifier onto the set of models that satisfy target group-fairness requirements. The new, projected model is given by post-processing the outputs of the pre-trained classifier by a multiplicative factor. We provide a parallelizable, iterative algorithm for computing the projected classifier and derive both sample complexity and convergence guarantees. Comprehensive numerical comparisons with state-of-the-art benchmarks demonstrate that our approach maintains competitive performance in terms of accuracy-fairness trade-off curves, while achieving favorable runtime on large datasets. We also evaluate our method at scale on an open dataset with multiple classes, multiple intersectional groups, and over 1M samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Variational Autoencoder for Collaborative Filtering 25

Hybrid Variational Autoencoder for Collaborative Filtering

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Liu, Jinxin Xiao, Yingyuan Zhu, Ke Zheng, Wenguang Hsu, Ching-Hsien Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China Asia University Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9781665405270

In recent years, Variational AutoEncoder (VAE) based methods have made many important achievements in the field of collaborative filtering recommendation system. VAE is a kind of Bayesian model which combines latent variable model with variational inference, but its optimization is often troubled by posterior collapse. By comparing the optimization process of VAE and ordinary autoencoder, we observe that the mismatch between poorly optimized encoder and decoder with too strong characterization capabilities makes it difficult to learn the mapping from the data manifold to the parameterized graph. Since the learning of a posteriori network corresponds to the encoder, we think that the problem of a posteriori collapse can be alleviated by balancing the encoder and decoder better. Therefore, we proposed Hy-VAE, which combines conventional VAE with deterministic autoencoder, and has the advantages of both VAE and deterministic autoencoder. Experiments on three real-world recommendation data sets show that our method alleviates the posterior crash problem in VAE and improves the recommendation performance. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

F2NAS: Flexible Federated Neural Architecture Search in Green Edge computing

F2NAS: Flexible Federated Neural Architecture Search in Gree...

引用

IEEE International Conference on Communications (ICC)

作者： Zebo Zhao Chao Qiu Yunfeng Zhao Xiaofei Wang Haipeng Yao Xiuhua Li F. Richard Yu College of Intelligence and Computing Tianjin University Tianjin China Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China Department of Systems and Computer Engineering Carleton University Ottawa Canada

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The rapid growth of edge computing calls for fine-tuned deep neural network (DNN) deployment that emphasizes energy-efficient implementation, due to the resource constraints of edge devices. Traditional Federated Learning-based Neural Architecture Search (FL-based NAS) has been instrumental in the complexities of this deployment, particularly in addressing constraints posed by device heterogeneity, limited resources, and privacy preservation. However, it is hindered by issues such as suboptimal aggregation of homogeneous neural blocks, significant knowledge waste in disregarding heterogeneous neural blocks, and excessive communication energy consumption. This paper introduces F 2 NAS in green edge computing, a novel energy-efficient approach that addresses these limitations by ensuring flexible and energy-efficient model design and training for edge devices. Firstly, F 2 NAS introduces an innovative aggregation strategy that enhances the integration of homogeneous neural blocks by using inter-block distances to optimize weight allocation. Further, it employs a unique parameter extraction technique that recaptures valuable insights from previously overlooked heterogeneous neural blocks. Finally, F 2 NAS meticulously calibrates communication energy consumption by balancing loss function and model interaction, setting and refining an upper limit for model communication. Experimental results reveal F 2 NAS enhances model accuracy by 2.8% to 4.7%, simultaneously reducing the energy consumption by nearly 50% through optimizing the communication cost.

关键词： Training Energy consumption Privacy Accuracy Computational modeling Refining Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Enhanced Area Triboelectric Nanogenerator Utilizing Recycled Single Used Plastic Bubble Wrap and Discarded Sketching Paper Ensuring Circularity of Material

Enhanced Area Triboelectric Nanogenerator Utilizing Recycled...

引用

Conference on Technologies for Sustainability (Sustech)

作者： Muhammad Umaid Bukhari Kashif Riaz Rehan Ahmed Adeel Arshad Khawaja Qasim Maqbool Arshad Khan Amine Bermak Abdelkrim Khelif Department of Computer and Software Engineering Information Technology University of the Punjab Lahore Pakistan Division of Computing and Information Technology College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Department of Electrical Engineering Information Technology University of the Punjab Lahore Pakistan Faculty of Engineering and Technology Superior University Lahore Pakistan Department of Computer Science Bahria University Lahore Pakistan

ISBN: (数字)9798331504311

ISBN: (纸本)9798331504328

Plastic pollution has become a major environmental challenge globally as millions of tons of plastic waste are entering oceans and landfills every year. The production and usage of plastic has surged due to its low cost and easy availability. This in turn leads to widespread usage of single-use plastics. Plastic waste takes centuries to degrade and when it decomposes, it breaks down into harmful microplastics that pollute the air, soil and water. This pollution of microplastics threatens wildlife, marine life and creates health risks for human beings. Moreover, plastic production and its waste release significant amounts of greenhouse gases which further contribute to climate change. As plastic waste is continuously accumulating in the environment its long-term effects on humans, climate and ecosystem are inevitable. On the other hand, the increased usage of electronic devices has transformed daily life and has raised concerns about the energy consumption of these devices and the generation of e-waste due to disposable batteries. Triboelectric nanogenerators (TENGs) have emerged as an innovative way to convert mechanical energy into electricity by utilizing frictional forces and vibrations. TENGs can be integrated into wearable electronics which in turn eliminates the need for frequent battery replacement and enhances sustainability. This study presents a low-cost triboelectric nanogenerator made from recycled bubble wrap and sketching paper (BW-TENG). BW-TENG offers an efficient and eco-friendly way to generate energy from common household waste materials. BW-TENG is capable of generating an open circuit voltage (V oc ) of 6.38 V, a short circuit current (I sc ) of 5.9 µA and a maximum output power of 7.84 µW respectively. BW TENG not only ensures the circularity of waste materials but also highlights the cost-effective manufacturing of a lightweight triboelectric nanogenerator.

关键词： Costs Nanogenerators Wildlife Production Water pollution Batteries Triboelectricity Sustainable development Power generation Plastic waste

来源：评论

学校读者我要写书评

暂无评论

A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

arXiv

引用

arXiv 2024年

作者： Xue, Yu Zhu, Chenchen Zhou, MengChu Wahib, Mohamed Gabbouj, Moncef School of Software Nanjing University of Information Science and Technology Jiangsu China Department of Electrical and Computer Engineering NewJersey Institute of Technology NewarkNJ07102 United States Japan Department of Computing Sciences Tampere University Tampere Finland

Neural architecture search (NAS) enables researchers to automatically explore vast search spaces and find efficient neural networks. But NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process, which requires a lot of computing resources and time. In order to improve the efficiency of NAS, a series of methods have been proposed to reduce the evaluation time of neural architectures. However, they are not efficient enough and still only focus on the accuracy of architectures. In addition to the classification accuracy, more efficient and smaller network architectures are required in real-world applications. To address the above problems, we propose the SMEM-NAS, a pairwise comparison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism. In the SMEM-NAS, a surrogate model is constructed based on pairwise comparison relations to predict the accuracy ranking of architectures, rather than the absolute accuracy. Moreover, two populations cooperate with each other in the search process, i.e., a main population guides the evolution, while a vice population expands the diversity. Our method aims to provide high-performance models that take into account multiple optimization objectives. We conduct a series of experiments on the CIFAR-10, CIFAR- 100 and ImageNet datasets to verify its effectiveness. With only a single GPU searching for 0.17 days, competitive architectures can be found by SMEM-NAS which achieves 78.91% accuracy with the MAdds of 570M on the ImageNet. This work makes a significant advance in the important field of NAS. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Multiview Deep Forest for Overall Survival Prediction in Cancer

引用

Computational and Mathematical Methods in Medicine 2023年第1期2023卷 7931321-7931321页

作者： Li, Qiucen Du, Zedong Chen, Zhikui Huang, Xiaodi Li, Qiu Dalian University of Technology School of Software China Chengdu Second People's Hospital Department of Oncology China Charles Sturt University School of Computing Mathematics and Engineering Australia West China Hospital Department of Oncology China

Overall survival (OS) in cancer is crucial for cancer treatment. Many machine learning methods have been applied to predict OS, but there are still the challenges of dealing with multiview data and overfitting. To overcome these problems, we propose a multiview deep forest (MVDF) in this paper. MVDF can learn the features of each view and fuse them with integrated learning and multiple kernel learning. Then, a gradient boost forest based on the information bottleneck theory is proposed to reduce redundant information and avoid overfitting. In addition, a pruning strategy for a cascaded forest is used to limit the impact of outlier data. Comprehensive experiments have been carried out on a data set from West China Hospital of Sichuan University and two public data sets. Results have demonstrated that our method outperforms the compared methods in predicting overall survival. © 2023 Qiucen Li et al.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Examining the Benefits of AI in Wearable Sensor-based Healthcare Solutions

Examining the Benefits of AI in Wearable Sensor-based Health...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Prashamsh Takkalapally Balaram Yadav Kasula Sachin C. Patil J. Logeshwaran Department of Engineering Computing and Mathematical Sciences Lewis University USA Dept of Information Technology University Of The Cumberlands Williamsburg KY USA Senior Software Engineer USA Department of Computer Science CHRIST (Deemed to be University) Bengaluru Karnataka India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The emergence of the AI generation has introduced adjustments to the manner healthcare solutions are advanced and applied. Wearable sensor-based total healthcare answers were revolutionized by leveraging AI in diverse packages. AI may be used to enhance the accuracy and precision of facts analysis, simplify information collection procedures, and pick out affected person-unique styles from the accrued data. Furthermore, AI can provide both actual-time and predictive analytics abilities, which are particularly useful for devising personalized healthcare offerings. Its provision of scalable systems hurries up the traits of various programs and has enabled personalized healthcare answers to be deployed in a shorter length. In spite of a number of the associated challenges, including data privacy troubles, AI-based wearable sensor-based healthcare answers can revolutionize patient tracking and timely detection of capability health conditions, improve preventive fitness care, and decrease healthcare fees.

关键词： Industries Data privacy Accuracy Medical services Artificial intelligence Prognostics and health management Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Microservices Centric In-network Computations for Internet of Vehicles

TechRxiv

引用

TechRxiv 2023年

作者： Salah ud din, Muhammad Atif ur Rehman, Muhammad Imran, Muhammad Kim, Byung Seo Department of Electronics & Computer Engineering Hongik University Sejong City30016 Korea Republic of Department of Computing & Mathematics Manchester Metropolitan University United Kingdom Department of Software and Communications Engineering Hongik University Sejong City30016 Korea Republic of

This paper presents the design and implementation of a multilayered microservices-centric in-network computation framework tailored for the Internet of Vehicular Networks. The proposed framework integrates a vehicular network layer, Edge computing layer, and Cloud to enhance network efficiency and minimize latency for time-critical vehicular applications. In the proposed work, modifications were made to the NDNsim codebase, integrating the C++ Boost Asio library to facilitate NDNsim-Edge communication for designated microservice computation. in additions, a microservice-centric driver assistance application is also emulated in Dotnet core with microservices deployed on various Edge and cloud servers. Moreover, Restful APIs have been developed, allowing the NDNsim layer, physical Edge layer, and Cloud stations to offload a microservice-centric computation request and retrieve the corresponding compute outcomes. Furthermore, the Entity framework is utilized to ensure proper tracking and management of the requests while an HTML-based user interface is developed for a visual representation of the request pattern. Extensive testbed experimentation revealed that the proposed framework highly optimized bandwidth consumption, reduces latency and amplifies the computed results delivery ratio compared with the conventional monolithic system. © 2023, CC BY.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes

Fed-CVLC: Compressing Federated Learning Communications with...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Xiaoxin Su Yipeng Zhou Laizhong Cui John C. S. Lui Jiangchuan Liu College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong HKSAR School of Computing Science Simon Fraser University Canada

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

In Federated Learning (FL) paradigm, a parameter server (PS) concurrently communicates with distributed participating clients for model collection, update aggregation, and model distribution over multiple rounds, without touching private data owned by individual clients. FL is appealing in preserving data privacy; yet the communication between the PS and scattered clients can be a severe bottleneck. Model compression algorithms, such as quantization and sparsification, have been suggested but they generally assume a fixed code length, which does not reflect the heterogeneity and variability of model updates. In this paper, through both analysis and experiments, we show strong evidences that variable-length is beneficial for compression in FL. We accordingly present Fed-CVLC (Federated Learning Compression with Variable-Length Codes), which fine-tunes the code length in response of the dynamics of model updates. We develop optimal tuning strategy that minimizes the loss function (equivalent to maximizing the model utility) subject to the budget for communication. We further demonstrate that Fed-CVLC is indeed a general compression design that bridges quantization and sparsification, with greater flexibility. Extensive experiments have been conducted with public datasets to demonstrate that Fed-CVLC remarkably outperforms state-of-the-art baselines, improving model utility by 1.50%-5.44%, or shrinking communication traffic by 16.67%-41.61%.

关键词： Training Data privacy Codes Quantization (signal) Federated learning Data models Servers

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：