检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhengrui Xu Guan'an Wang Xiaowen Huang Jitao Sang School of Computer Science and Technology Beijing Jiaotong University School of Computer Science and Technology Beijing Jiaotong University and Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University and Key Laboratory of Big Data & Artificial Intelligence in Transportation(Beijing Jiaotong University) Ministry of Education

ISBN: (纸本)9798331314385

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors" [4]. In this paper, we propose a novel Denoising Model for Representation Learning (DenoiseRep) to improve feature discrimination with joint feature extraction and denoising. DenoiseRep views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, DenoiseRep fus es the parameters of feature extraction and denoising layers, and theoretically demonstrates its equivalence before and after the fusion, thus making feature denoising computation-free. DenoiseRep is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures. Code is available at https://***/wangguanan/DenoiseRep.

关键词：

来源：评论

学校读者我要写书评

暂无评论

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Network for Segmenting Pathology Lesion of the Focal Lymphocytic Sialadenitis 1

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Ne...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Han, Hao Lu, Feng Deng, Yanhan Luo, Xiaofang Jin, Hai Tu, Wei Xie, Xia 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 Cluster and Grid Computing Lab Wuhan430074 China Tongji Medical College Huazhong University of Science and Technology Tongji Hospital Wuhan430022 China School of Computer Science and Technology Hainan University Haikou China

ISBN: (纸本)9798350358780

In the medical realm, the pivotal role of pathological Whole Slide Images (WSIs) in detecting cancer, tracking disease progression, and evaluating treatment efficacy is indisputable. Nevertheless, the identification and quantification of lesion areas in these gigapixel WSIs present a significant challenge due to their substantial size and the intricate details of lesions. To address these issues, we developed a novel multi-resolution and multi-scale cross fusion network (M2CF-Net), adept at managing large-scale pathological WSIs and capturing both fine details and context. Our model particularly focuses on segmenting local lymphocyte infiltration lesions in pathological WSIs of patients diagnosed with primary Sjogren's syndrome. By employing a patch-based training approach and combining interconnected elements via a multi-scale fusion technique, we enhance our model's capacity to detect and analyze structures and features in minor salivary gland section WSIs. Extensive experiments and ablation studies conducted on real-world clinical datasets affirm our model's superior accuracy in identifying lymphocyte-infiltrated regions over state-of-the-art models, with a performance improvement of up to 4.32% in terms of the Dice Similarity Coefficient. © 2023 IEEE.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving graph publishing with disentangled variational information bottleneck

Privacy-preserving graph publishing with disentangled variat...

引用

作者： Ma, Liya Li, Chen Sun, Siqi Guo, Shu Wang, Lihong Li, Jianxin School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China ARC LAB Tencent Shenzhen China China Academy of Industrial Internet Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China

Social networks collect enormous amounts of user personal and behavioral data, which could threaten users' privacy if published or shared directly. Privacy-preserving graph publishing (PPGP) can make user data available while protecting private information. For this purpose, in PPGP, anonymization methods like perturbation and generalization are commonly used. However, traditional anonymization methods are challenging in balancing high-level privacy and utility, ineffective at defending against both various link and hybrid inference attacks, as well as vulnerable to graph neural network (GNN)-based attacks. To solve those problems, we present a novel privacy-disentangled approach that disentangles private and non-private information for a better privacy-utility trade-off. Moreover, we propose a unified graph deep learning framework for PPGP, denoted privacy-disentangled variational information bottleneck (PDVIB). Using low-dimensional perturbations, the model generates an anonymized graph to defend against various inference attacks, including GNN-based attacks. Particularly, the model fits various privacy settings by employing adjustable perturbations at the node level. With three real-world datasets, PDVIB is demonstrated to generate robust anonymous graphs that defend against various privacy inference attacks while maintaining the utility of non-private information. © 2023 John Wiley & Sons Ltd.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Energy Efficient Communication for Large-Scale Industrial Internet of Things 2nd

Real-Time Energy Efficient Communication for Large-Scale Ind...

引用

2nd International Conference on Sustainability: Developments and Innovations, ICSDI 2024

作者： Khan, Musfira Khan, Muazzam A. Farman, Haleem Malik, Asad W. Ramzan, Muhammad Sher Islamabad Pakistan Department of Computer Science Quaid-I-Azam University Islamabad Pakistan ICESCO Chair for Big Data Analytics and Edge Computing Quaid-I-Azam University Islamabad Pakistan Smart Systems Engineering Lab College of Engineering Prince Sultan University Riyadh Saudi Arabia King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9789819783441

Industrial Internet of Things (IIoTs) comprises large-scale sensors deployed to monitor and control the system. Deploying IoT devices presents challenges due to frequent disconnections and sudden power drainage in intermediate devices responsible for routing data. Consequently, the deployed network becomes sporadic, hindering connectivity with the industrial controller system, especially critical during emergencies. Furthermore, IoT node failures lead to a short network lifetime, which is intolerable in real-time industrial applications. This paper introduces a multi-hop clustering framework designed for reliable communication in industrial environments. The framework dynamically forms clusters, employing cluster heads and backup nodes to stabilize communication in the absence of a cluster head. Each cluster selects a backup node during the initial cluster head selection and later through data piggybacking. The proposed framework provides efficient communication across the IIoT network with the help of a backup and multi-hop clustering mechanism. The proposed framework is compared with two existing protocols i.e. cluster-based coordination routing (CRC) and energy-efficient quality of service routing (EEQSRP) protocols. The results show a considerable decrease in sensor energy consumption and packet delay. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Novel Distributed Forecasting Method Based on Information Fusion and Incremental Learning for Streaming Time Series

SSRN

引用

SSRN 2023年

作者： Melgar-García, Laura Gutiérrez-Avilés, David Rubio-Escudero, Cristina Troncoso, Alicia Data Science & Big Data Lab Pablo de Olavide University SevilleES-41013 Spain Department of Computer Science University of Seville Avda. Reina Mercedes s/n Seville41012 Spain

Real-time algorithms have to adapt and adjust to new incoming patterns to provide timely and accurate responses. This paper presents a new distributed forecasting algorithm for streaming time series called StreamWNN. StreamWNN starts with an offline stage in which a forecasting model based on tuples of information fusion is created with historical data. In particular, this model consists of the fusion of patterns composed of past values of the time series with the future values of their k-nearest neighbors. Afterwards, streaming data starts to arrive. The model is incrementally updated in the online stage using a buffer with streaming data that more accurately matches the current model patterns. The model can be updated daily, monthly, quarterly or based on error thresholds. The methodology has been applied to Spanish electricity demand time series providing more accurate results when the model is updated incrementally. The best results are obtained with the daily update of the model, resulting in an error between 2% and 3.5% depending on the prediction horizon. The model provides better results than other algorithms. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

FLOW-TSVAD: TARGET-SPEAKER VOICE ACTIVITY DETECTION VIA LATENT FLOW MATCHING

arXiv

引用

arXiv 2024年

作者： Chen, Zhengyang Han, Bing Wang, Shuai Jiang, Yidi Qian, Yanmin AudioCC Lab CS Dept Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China National University of Singapore Singapore

Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm and our proposed Flow-TSVAD method outperforms the Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, requiring only two inference steps to achieve promising results. As a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times. Moreover, ensembling results from various sampling instances further enhances diarization performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

FedEdge: Accelerating Edge-Assisted Federated Learning 23

FedEdge: Accelerating Edge-Assisted Federated Learning

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Federated learning (FL) has been widely acknowledged as a promising solution to training machine learning (ML) model training with privacy preservation. To reduce the traffic overheads incurred by FL systems, edge servers have been included between clients and the parameter server to aggregate clients' local models. Recent studies on this edge-assisted hierarchical FL scheme have focused on ensuring or accelerating model convergence by coping with various factors, e.g., uncertain network conditions, unreliable clients, heterogeneous compute resources, etc. This paper presents our three new discoveries of the edge-assisted hierarchical FL scheme: 1) it wastes significant time during its two-phase training rounds;2) it does not recognize or utilize model diversity when producing a global model;and 3) it is vulnerable to model poisoning attacks. To overcome these drawbacks, we propose FedEdge, a novel edge-assisted hierarchical FL scheme that accelerates model training with asynchronous local federated training and adaptive model aggregation. Extensive experiments are conducted on two widely-used public datasets. The results demonstrate that, compared with state-of-the-art FL schemes, FedEdge accelerates model convergence by 1.14 × -3.20 ×, and improves model accuracy by 2.14% - 6.63%. © 2023 ACM.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

ImagineNet: Target Speaker Extraction with Intermittent Visual Cue Through Embedding Inpainting

ImagineNet: Target Speaker Extraction with Intermittent Visu...

引用

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

作者： Zexu Pan Wupeng Wang Marvin Borsdorf Haizhou Li Institute of Data Science National University of Singapore (NUS) Singapore Department of Electrical and Computer Engineering NUS Singapore Machine Listening Lab University of Bremen Germany Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China

The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary attention. Either a pre-recorded utterance or a synchronized lip movement in a video clip can serve as the auxiliary reference. The use of visual cue is not only feasible, but also effective due to its noise robustness, and becoming popular. However, it is difficult to guarantee that such parallel visual cue is always available in real-world applications where visual occlusion or intermittent communication can occur. In this paper, we study the audio-visual speaker extraction algorithms with intermittent visual cue. We propose a joint speaker extraction and visual embedding inpainting framework to explore the mutual benefits. To encourage the interaction between the two tasks, they are performed alternately with an interlacing structure and optimized jointly. We also propose two types of visual inpainting losses and study our proposed method with two types of popularly used visual embeddings. The experimental results show that we outperform the baseline in terms of signal quality, perceptual quality, and intelligibility.

关键词： Visualization Lips Design methodology Signal processing algorithms Signal processing Noise robustness Synchronization

来源：评论

学校读者我要写书评

暂无评论

Towards trustworthy blockchain systems in the era of “Internet of value”: development, challenges, and future trends

引用

science China(Information sciences) 2022年第5期65卷 250-260页

作者： Hai JIN Jiang XIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology

Since the advent of cryptocurrencies such as Bitcoin, blockchain, as their underlying technologies,has drawn a massive amount of attention from both academia and the industry. This ever-evolving technology inherits the “genes” of distributed systems, offering significant advantages of immutability, transparency,auditability, and tamper-resistance. These benefits help blockchain re-establish public confidence, and hold the significant promise of reliable information sharing and value transfer. Therefore, blockchain has become the foundation of crucial strategic deployments in countries across the world, and the fundamental basis for building the next generation Web 3.0 — “Internet of value”. In this article, we will start with unraveling the essential ingredients of blockchain technology, and showing the characteristics of each of these ingredients in the context of distributed systems. We will then present the core technical challenges that need to be addressed prior to unleashing its full potential, including its performance, scalability, and cross-chain interoperability. Finally, we will introduce the recent developments of blockchain systems, and discuss the future trends of the blockchain ecosystem.

关键词： blockchain distributed systems internet of value challenges development

来源：评论

学校读者我要写书评

暂无评论

Nearest neighbors with incremental learning for real-time forecasting of electricity demand

Nearest neighbors with incremental learning for real-time fo...

引用

IEEE International Conference on data Mining Workshops (ICDM Workshops)

作者： Laura Melgar-García David Gutiérrez-Avilés Cristina Rubio-Escudero Alicia Troncoso Data Science & Big Data Lab Pablo de Olavide University Seville Spain Department of Computer Science University of Seville Seville Spain

Electricity demand forecasting is very useful for the different actors involved in the energy sector to plan the supply chain (generation, storage and distribution of energy). Nowadays energy demand data are streaming data coming from smart meters and has to be processed in real-time for more efficient demand management. In addition, this kind of data can present changes over time such as new patterns, new trends, etc. Therefore, real-time forecasting algorithms have to adapt and adjust to online arriving data in order to provide timely and accurate responses. This work presents a new algorithm for electricity demand forecasting in real-time. The proposed algorithm generates a prediction model based on the K-nearest neighbors algorithm, which is incrementally updated as online data arrives. Both time-frequency and error threshold based model updates have been evaluated. Results using Spanish electricity demand data with a ten-minute sampling frequency rate are reported, reaching 2% error with the best prediction model obtained when the update is daily.

关键词： Time-frequency analysis Computational modeling Time series analysis Supply chains Demand forecasting Predictive models Prediction algorithms

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：