检索结果-内蒙古大学图书馆

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Wu, Junkang Chen, Jiawei Wu, Jiancan Shi, Wentao Zhang, Jizhi Wang, Xiang University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition Hefei China Zhejiang Unversity The State Key Laboratory of Blockchain and Data Security China Institute of Artificial Intelligence Institute of Dataspace Hefei Comprehensive National Science Center. China

ISBN: (纸本)9798350317152

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL) stands out for not only achieving remarkable accuracy but also better robustness and fairness. Nevertheless, the current literature lacks a comprehensive explanation for the efficacy of SL. Toward addressing this research gap, we conduct theoretical analyses on SL and uncover three insights: 1) Optimizing SL is equivalent to performing Distributionally Robust Optimization (DRO) on the negative data, thereby learning against perturbations on the negative distribution and yielding robustness to noisy negatives. 2) Comparing with other loss functions, SL implicitly penalizes the prediction variance, resulting in a smaller gap between predicted values and and thus producing fairer results. Building on these insights, we further propose a novel loss function Bilateral SoftMax Loss (BSL) that extends the advantage of SL to both positive and negative sides. BSL augments SL by applying the same Log-Expectation-Exp structure to positive examples as is used for negatives, making the model robust to the noisy positives as well. Remarkably, BSL is simple and easy-to-implement -requiring just one additional line of code compared to SL. Experiments on four real-world datasets and three representative backbones demonstrate the effectiveness of our proposal. The code is available at https://***/junkangwu/BSL. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Federated Learning on Non-IID data via Inversing Artificial Gradients

Byzantine-Robust Federated Learning on Non-IID Data via Inve...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Minyang Tang, Xiangyun Zhang, Tao Liu, Guangyuan Weng, Yu Minzu University of China Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance China Beijing Jiaotong University School of Software Engineering China Nanyang Technological University College of Computing and Data Science Singapore

ISBN: (纸本)9798350351255

Federated Learning (FL) is a distributed machine learning framework that enhances privacy by enabling multiple participants to train a global model without sharing their raw data. However, FL still faces the threat posed by data and Byzantine attacks (e.g., data poisoning and model poisoning attacks) from malicious clients aimed to decrease the FL global training accuracy. Previous studies have proposed solutions to improve the robustness of FL systems. However, these robust approaches have not effectively defended against Byzantine attacks from malicious clients in non-Independent and Identically Distributed (non-IID) environments, decreasing overall training accuracy. In this work to address this issues, we propose a new defence framework that aims to enhance model accuracy against Byzantine attacks from malicious clients in non-IID environments. In our approach, the central server performs the Inverse Deep Learning Gradient attack using the gradient data submitted by users in each round, obtaining an inversed artificial gradient. We then assess the squared L2 norm difference between this inversed gradient and the actual gradients to detect malicious clients. Simultaneously, we assign weights to each client involved in the aggregation based on differences in the squared L2 norm, aiming to minimize the impact of malicious actors on the overall model. We have experimentally evaluated our method and demonstrated its ability to maintain training accuracy under attack in non-IID environments using standard datasets. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust Network For Segmenting Roof Planes From Sparse Point Clouds 36

Robust Network For Segmenting Roof Planes From Sparse Point ...

引用

36th International Conference on Software Engineering and Knowledge Engineering, SEKE 2024

作者： Fu, Hang Zeng, Cheng Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Wuhan China School of Computer and Information Engineering Hubei University Wuhan China School of Artificial Intelligence Hubei University Wuhan China

ISBN: (纸本)1891706594

The plane is the fundamental characteristic for describing the shape of polyhedral buildings. Roof plane segmentation of airborne LiDAR point clouds is an important step in 3D building model reconstruction. Existing methods are either non-automatic and efficient traditional methods, or hindered by the lack of datasets for roof plane segmentation and therefore fail to achieve good training for deep learning methods. To address the above issues, we proposes an end-to-end network called PUTr for roof plane segmentation of sparse point clouds. This network integrates a Point-cloud Upsampling module and Transformer to ensure effective generalization even when trained on low-density datasets, while also capturing dependency relationships within point cloud neighborhoods. Our model overcomes the low automation and manual intervention of existing methods, and the limited generalization of deep learning due to scarce high-quality datasets. Evaluations also demonstrate its effectiveness in roof plane segmentation of laser point cloud data. © 2024 Knowledge systems Institute Graduate School. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

FedCSA: Boosting the Convergence Speed of Federated Unlearning under data Heterogeneity 21

FedCSA: Boosting the Convergence Speed of Federated Unlearni...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Wang, Zhen Alghazzawi, Daniyal M Cheng, Li Liu, Gaoyang Wang, Chen Cheng, Zeng Yang, Yang Hubei University Key Laboratory of Intelligent Sensing System and Security Ministry of Education School of Artificial Intelligence Wuhan China King Abdulaziz University Jeddah Saudi Arabia Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350329223

The exponential growth of the Internet and the widespread availability of personal data have raised significant concerns regarding personal privacy and societal security. In response, the 'right to be forgotten' has emerged as a fundamental principle, empowering individuals to request the removal of their personal data. Though relieving the privacy concerns at a certain degree by doing so, Artificial Intelligence (AI) models, trained by personal data, still suffers from privacy leakage risks. Therefore, machine unlearning attracts great attention from both industry and academia, aiming at erasing the risks of privacy leakage of AI models. However, existing machine unlearning methods primarily operate within centralized frame-works, limiting their applicability to decentralized Federated Learning (FL) settings where data is decentralized and not directly accessible. Additionally, current federated unlearning methods only approximate data deletion, leaving a potential risk of data leakage. To address these issues, this paper presents FedCSA, The FedCSA approach adopts a divide-and-conquer strategy by clustering and slicing the users' data. Subsequently, submodels are trained on each individual slice, and their aggregation yields the global model. During the unlearning task, only the corresponding sub-model undergoes retraining, significantly reducing training time while ensuring data privacy and achieving precise data deletion. Extensive experiments are conducted on real-world datasets, including MNIST, Fashion-MNIST, and CIFAR-10, to evaluate the performance of FedCSA. The results demonstrate that FedCSA outperforms state-of-the-art machine learning methods, such as retrain and SISA, in terms of efficiency and global model performance. Our code is publicly available at https://***/ZhenWang9/FedCSA. © 2023 IEEE.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Design Guidance for Lightweight Object Detection Models 3rd

Design Guidance for Lightweight Object Detection Models

引用

3rd International Conference on Big data and security, ICBDS 2021

作者： Wang, Rui Wang, Xueli Chen, Yunfang Zhang, Wei School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China

ISBN: (纸本)9789811908514

The lightweight target detection model is deployed in an environment with limited computing power and power consumption, which is widely used in many fields. Most of the current lightweight technologies only focus on a few steps of the model implementation and lack a global perspective. Therefore, this paper proposes a general lightweight model implementation framework, including network construction indicators, lightweight backbone network design, and model optimization. By analyzing the complexity indicator of network structure, the factors that affect network performance such as depth and width are summarized. On this basis, combine the One-Shot Aggregation (OSA) idea and Cross-Stage Partial Network (CSPNet) transformation to construct a general lightweight detection network CSPOSA. Further specific optimization strategies are proposed to prune the network structure and training process. For the network structure, the width and depth of the network are adjusted, the amount of parameters of the model is compressed. The training process is divided into the first, middle and last three stages to improve the detection performance of the model without adding extra computation. Taking embedded platform helmet detection as the experimental scene, the parameter amount of the realized model is 1/10 of the mainstream models YOLOv3 and YOLOv4, and the detection accuracy is similar, so it is more suitable for deployment on devices with limited computing power. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

Estimating Power Consumption of Containers and Virtual Machines in data Centers

Estimating Power Consumption of Containers and Virtual Machi...

引用

IEEE International Conference on Cluster Computing

作者： Xusheng Zhang Ziyu Shen Bin Xia Zheng Liu Yun Li Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications

ISBN: (数字)9781728166773

ISBN: (纸本)9781728166780

Virtualization technologies provide solutions of cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many effective models for estimating power consumption of virtual machines (VM) have been proposed, few power estimation models of containers have been put forth. In this paper, we offer a fast-training piecewise regression model based on decision tree to build a VM power estimation model and estimate the containers' power by treating the container as a group of processes on the VM. In our model, we characterize the nonlinear relationship between power and features and realize the effective estimation of the containers on the VM. We evaluate the proposed model on 13 workloads in PARSEC and compare it with several models. The experimental results prove the effectiveness of our proposed model on most workloads. Moreover, the estimated power of the containers is in line with expectations.

关键词： Power demand Processor scheduling Estimation Containers Virtual machining data models Virtualization

来源：评论

学校读者我要写书评

暂无评论

Disentangling Client Contributions: Improving Federated Learning Accuracy in the Presence of Heterogeneous data 21

Disentangling Client Contributions: Improving Federated Lear...

引用

作者： Liu, Chunming Alghazzawi, Daniyal M Cheng, Li Liu, Gaoyang Wang, Chen Zeng, Cheng Yang, Yang Hubei University Key Laboratory of Intelligent Sensing System and Security Ministry of Education School of Artificial Intelligence Wuhan China King Abdulaziz University Jeddah Saudi Arabia Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350329223

Federated Learning (FL) is a promising paradigm that leverages distributed data sources to train machine learning models, thereby offering significant privacy advantages. However, the inherent statistical heterogeneity among clients, characterized by distinct data distributions and varying model performance, poses a substantial challenge. Such heterogeneity adversely affects both the convergence and overall performance of the global model within the FL framework. To address this issue, we introduce a novel FL algorithm, FedVa, which considers both the local data volume and model accuracy to determine client contributions, assigning respective weights. This consideration facilitates greater engagement from key clients during the aggregation process, thereby enhancing their influence on the global model refinement. Experimental results indicate that FedVa surpasses prevailing methods in managing statistical heterogeneity and enhancing global model accuracy, without incurring additional communication costs. Specifically, FedVa achieves a convergence speed 3.9 times faster than FedAvg on the MNIST dataset, and on the CIFAR-10 dataset, it results in a 2.3% increase in final model accuracy compared to FedAvg. Our code is publicly available at https://***/ChunmingLiu23/FedVa. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Hash Function Based on Quantum Walks with Two-Step Memory

Hash Function Based on Quantum Walks with Two-Step Memory

引用

2024 International Conference on Computing, Machine Learning and data Science, CMLDS 2024

作者： Zhou, Qing Lu, Songfeng Yang, Hao Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute Guangdong Shenzhen China

ISBN: (纸本)9798400716393

We propose a new quantum-walk-based hash function QHF2M by combining two types of quantum walks with two-step memory and numerically test its statistical performance. The test result shows that QHF2M is on a par with the state-of-the-art hash functions based on discrete quantum walks in terms of sensitivity of hash value to message, diffusion and confusion properties, uniform distribution property, and collision resistance property. Moreover, both unequal and equivalent coin angles used by the underlying quantum walks can lead to near-ideal statistical performance. This result indicates that neither using quantum walks with different memory length nor adopting distinct coin angles is a necessary condition for constructing good quantum-walk-with-memory-based hash functions. © 2024 ACM.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

GBCT: An Efficient and Adaptive Granular-Ball Clustering Algorithm for Complex data

arXiv

引用

arXiv 2024年

作者： Xia, Shuyin Shi, Bolun Wang, Yifan Xie, Jiang Wang, Guoyin Gao, Xinbo Chongqing Key Laboratory of Computational Intelligence The Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education The Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points. This way is not inconsistent with the cognitive mechanism of "global precedence" in human brain, resulting in those methods’ bad performance in efficiency, generalization ability and robustness. To address this problem, we propose a new clustering algorithm called granular-ball clustering (GBCT) via granular-ball computing. Firstly, GBCT generates a smaller number of granular-balls to represent the original data, and forms clusters according to the relationship between granular-balls, instead of the traditional point relationship. At the same time, its coarse-grained characteristics are not susceptible to noise, and the algorithm is efficient and robust;besides, as granular-balls can fit various complex data, GBCT performs much better in non-spherical data sets than other traditional clustering methods. The completely new coarse granularity representation method of GBCT and cluster formation mode can also used to improve other traditional methods. All codes can be available from the following link. Copyright © 2024, The Authors. All rights reserved.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

Granular-ball Representation Learning for Deep CNN on Learning with Label Noise

arXiv

引用

arXiv 2024年

作者： Dai, Dawei Zhu, Hao Xia, Shuyin Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

In actual scenarios, whether manually or automatically annotated, label noise is inevitably generated in the training data, which can affect the effectiveness of deep CNN models. The popular solutions require data cleaning or designing additional optimizations to punish the data with mislabeled data, thereby enhancing the robustness of models. However, these methods come at the cost of weakening or even losing some data during the training process. As we know, content is the inherent attribute of an image that does not change with changes in annotations. In this study, we propose a general granular-ball computing (GBC) module that can be embedded into a CNN model, where the classifier finally predicts the label of granular-ball (gb) samples instead of each individual samples. Specifically, considering the classification task: (1) in forward process, we split the input samples as gb samples at feature-level, each of which can correspond to multiple samples with varying numbers and share one single label;(2) during the backpropagation process, we modify the gradient allocation strategy of the GBC module to enable it to propagate normally;and (3) we develop an experience replay policy to ensure the stability of the training process. Experiments demonstrate that the proposed method can improve the robustness of CNN models with no additional data or optimization. Copyright © 2024, The Authors. All rights reserved.

关键词： Image annotation

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：