检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ge, Songyang Chang, Tsung-Hui The Shenzhen Research Institute of Big Data The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China

Stochastic distributed optimization methods that solve an optimization problem over a multi-agent network have played an important role in a variety of large-scale signal processing and machine leaning applications. Among the existing methods, the gradient tracking (GT) method is found robust against the variance between agents’ local data distribution, in contrast to the distributed stochastic gradient descent (SGD) methods which have a slowed convergence speed when the agents have heterogeneous data distributions. However, the GT method can be communication expensive due to the need of a large number of iterations for convergence. In this paper, we intend to reduce the communication cost of the GT method by integrating it with the local SGD technique. Specifically, we propose a new local stochastic GT (LSGT) algorithm where, within each communication round, the agents perform multiple SGD updates locally. Theoretically, we build the convergence conditions of the _LSGT algorithm and show that it can have an improved convergence rate of O(1/√ET), where E is the number of local SGD updates and T is the number of communication rounds. We further extend the LSGT algorithm to solve a more complex learning problem which has linearly coupled variables inside the objective function. Experiment results demonstrate that the proposed algorithms have significantly improved convergence speed even under heterogeneous data distribution. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

DETECTING OUT-OF-DISTRIBUTION SAMPLES VIA CONDITIONAL DISTRIBUTION ENTROPY WITH OPTIMAL TRANSPORT

arXiv

引用

arXiv 2024年

作者： Feng, Chuanwen Chen, Wenlong Ke, Ao Ren, Yilong Xie, Xike Zhou, S. Kevin School of Biomedical Engineering University of Science and Technology of China China Data Darkness Lab MIRACLE Center Suzhou Institute for Advanced Research USTC China

When deploying a trained machine learning model in the real world, it is inevitable to receive inputs from out-of-distribution (OOD) sources. For instance, in continual learning settings, it is common to encounter OOD samples due to the non-stationarity of a domain. More generally, when we have access to a set of test inputs, the existing rich line of OOD detection solutions, especially the recent promise of distance-based methods, falls short in effectively utilizing the distribution information from training samples and test inputs. In this paper, we argue that empirical probability distributions that incorporate geometric information from both training samples and test inputs can be highly beneficial for OOD detection in the presence of test inputs available. To address this, we propose to model OOD detection as a discrete optimal transport problem. Within the framework of optimal transport, we propose a novel score function known as the conditional distribution entropy to quantify the uncertainty of a test input being an OOD sample. Our proposal inherits the merits of certain distance-based methods while eliminating the reliance on distribution assumptions, a-prior knowledge, and specific training mechanisms. Extensive experiments conducted on benchmark datasets demonstrate that our method outperforms its competitors in OOD detection. Copyright © 2024, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction 39

MSR: A Multifaceted Self-Retrieval Framework for Microscopic...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hong, Dongsheng Chen, Chao Li, Xujia Wang, Shuhui Lin, Wen Liao, Xiangwen College of Computer and Data Science Fuzhou University China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Hong Kong University of Science and Technology Hong Kong College of Computer and Control Engineering Minjiang University China

ISBN: (纸本)157735897X

The microscopic cascade prediction task has wide applications in downstream areas like "rumor detection". Its goal is to forecast the diffusion routines of information cascade within networks. Existing works typically formulate it as a classification task, which fails to well align with the Social Homophily assumption, as it just use the features of "infected" users while neglecting those of "uninfected" users in representation learning. Moreover, these methods focus primarily on social relationships, thereby dismissing other vital dimensions like users' historical behavior and the underlying preferences behind it. To address these challenges, we introduce the MSR (Multifaceted Self-Retrieval) framework. During encoding, in addition to the existing social graph, we construct a preference graph to represent "behavioral preferences" and further propose a modified multi-channel GRAU for multi-view analysis of cascade phenomenon. For decoding, our approach diverges from classification-based methods by reformulating the task as an information retrieval problem that predicts the target user with similarity measures. Empirical evaluations on public datasets demonstrate that this framework significantly outperforms baselines on Hits@κ and MAP@κ, affirming its enhanced ability. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Analysis of Product Sales Volume and Pricing Based on Multivariate Linear Regression Model and Time Series Forecasting Algorithm

Analysis of Product Sales Volume and Pricing Based on Multiv...

引用

Sensors, Electronics and Computer Engineering (ICSECE), IEEE International Conference on

作者： Linjie Zhou Haolei Yang SWUFE-UD Institute of Data Science Southwestern University of Finance and Economics Chengdu China School of Mathematics Southwestern University of Finance and Economics Chengdu China

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373653

This paper presents an analysis of product sales and pricing based on a multi-linear regression model and time series forecasting algorithm. Initially, historical sales prices are considered cost-plus pricing. A multi-linear regression model is then established, with the monthly sales volume of each product category as the dependent variable and the cost-plus pricing of products within the category as the independent variable, to ascertain the relationship between sales volume, cost-plus pricing, and expected profit rates for each product category. Subsequently, utilizing data from the first seven days of July for the previous three years and considering the sales of individual products and historical wholesale prices, a time series forecasting algorithm is developed to predict the wholesale prices of products sold from July 1 to July 7, 2023. Finally, an objective programming model is constructed, with the expected profit rates as decision variables and the maximization of supermarket profits as the objective, to establish constraints and compute the pricing and sales volume for 31 saleable products. The maximum profit for the supermarket over 7 days is determined to be 12808.92568 RMB.

关键词： Solid modeling Analytical models Computational modeling Heuristic algorithms Time series analysis Pricing Predictive models Programming Strategic planning Forecasting

来源：评论

学校读者我要写书评

暂无评论

Dynamic Searchable Scheme with Forward Privacy for Encrypted Document Similarity 22

Dynamic Searchable Scheme with Forward Privacy for Encrypted...

引用

22nd IEEE International Conference on Trust, Security and Privacy in computing and Communications, TrustCom 2023

作者： Al Sibahee, Mustafa A. Luo, Chengwen Zhang, Jin Huang, Yijing Abduljabbar, Zaid Ameen Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Iraq University College Computer Technology Engineering Department Basrah61004 Iraq University of Basrah College of Education for Pure Sciences Department of Computer Science Basrah61004 Iraq Huazhong University of Science and Technology Shenzhen Institute Shenzhen518000 China

ISBN: (纸本)9798350381993

Document retrieval plays an essential role in many real-world applications especially when the data storage is outsourced. Due to the great advantages offered by cloud computing, clients tend to outsource their personal data to remote servers maintained by external service providers. This raises serious privacy concerns about outsourced data because such providers are usually considered untrusted entities. The majority of previous schemes of document similarity search share the same limitation: they focus mainly on static collections. Dynamic searchable schemes (DSE) allow adding or removing documents at the expense of more leakage than static schemes. To thwart certain attacks, DSE schemes should support forward privacy property, which ensures that newly added documents cannot be related to previously issued search queries. We design and implement dynamic secure similarity search schemes with forward privacy for textual documents utilizing simhash method for hamming similarity. Our scheme provides an efficient search time and a sufficient level of privacy. To show the practicality of our proposed scheme, we performed excremental results with large document collections. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Keeping Pace with Ever-Increasing data: Towards Continual Learning of Code Intelligence Models

arXiv

引用

arXiv 2023年

作者： Gao, Shuzheng Zhang, Hongyu Gao, Cuiyun Wang, Chaozheng School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Big Data and Software Engineering Chongqing University China

—Previous research on code intelligence usually trains a deep learning model on a fixed dataset in an offline manner. However, in real-world scenarios, new code repositories emerge incessantly, and the carried new knowledge is beneficial for providing up-to-date code intelligence services to developers. In this paper, we aim at the following problem: How to enable code intelligence models to continually learn from ever-increasing data? One major challenge here is catastrophic forgetting, meaning that the model can easily forget knowledge learned from previous datasets when learning from the new dataset. To tackle this challenge, we propose REPEAT, a novel method for continual learning of code intelligence models. Specifically, REPEAT addresses the catastrophic forgetting problem with representative exemplars replay and adaptive parameter regularization. The representative exemplars replay component selects informative and diverse exemplars in each dataset and uses them to retrain model periodically. The adaptive parameter regularization component recognizes important parameters in the model and adaptively penalizes their changes to preserve the knowledge learned before. We evaluate the proposed approach on three code intelligence tasks including code summarization, software vulnerability detection, and code clone detection. Extensive experiments demonstrate that REPEAT consistently outperforms baseline methods on all tasks. For example, REPEAT improves the conventional fine-tuning method by 1.22, 5.61, and 1.72 on code summarization, vulnerability detection and clone detection, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

Downstream-agnostic Adversarial Examples

引用

International Conference on Computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physics-aware cross-domain fusion aids learning-driven computer-generated holography

引用

Photonics Research 2024年第12期12卷 2747-2756页

作者： GANZHANGQIN YUAN MI ZHOU FEI LIU MU KU CHEN KUI JIANG YIFAN PENG ZIHAN GENG Institute of Data and Information Tsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhen 518071China School of Optoelectronic Engineering Xidian UniversityXi’an 710071China Department of Electrical Engineering City University of Hong KongHong Kong SARChina School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China Department of Electrical and Electronic Engineering The University of Hong KongHong Kong SARChina Department of Computer Science The University of Hong KongHong Kong SARChina

The rapid advancement of computer-generated holography has bridged deep learning with traditional optical principles in recent ***,a critical challenge in this evolution is the efficient and accurate conversion from the amplitude to phase domain for high-quality phase-only hologram(POH)*** computational models often struggle to address the inherent complexities of optical phenomena,compromising the conversion *** this study,we present the cross-domain fusion network(CDFN),an architecture designed to tackle the complexities involved in POH *** CDFN employs a multi-stage(MS)mechanism to progressively learn the translation from amplitude to phase domain,complemented by the deep supervision(DS)strategy of middle features to enhance task-relevant feature learning from the initial ***,we propose an infinite phase mapper(IPM),a phase-mapping function that circumvents the limitations of conventional activation functions and encapsulates the physical essence of *** simulations,our proposed method successfully reconstructs high-quality 2K color images from the DIV2K dataset,achieving an average PSNR of 31.68 dB and SSIM of ***,we realize high-quality color image reconstruction in optical *** experimental results highlight the computational intelligence and optical fidelity achieved by our proposed physics-aware cross-domain fusion.

关键词： computer cross holography

来源：评论

学校读者我要写书评

暂无评论

Control Design of Nonlinear ODE/Transport PDE Cascaded Systems with Varying Propagation Speed 42

Control Design of Nonlinear ODE/Transport PDE Cascaded Syste...

引用

42nd Chinese Control Conference, CCC 2023

作者： Cai, Xiushan Lin, Yuhang Wang, Ping Ke, Changwu School of Data Science and Intelligent Engineering Xiamen Institute of Technology Xiamen361021 China College of Engineering North Carolina State University RaleighNC27695 United States College of Electrical Engineering and Automation Hubei Normal University Huangshi435002 China

ISBN: (纸本)9789887581543

We consider control design for a nonlinear ordinary differential equation (ODE) and transport partial differential equation (PDE) cascaded system whose propagation speed is spatially-varying. The ODE state is driven by the uncontrolled boundary of the transport PDE. Our nonlinear delay-compensated control law enables global asymptotic stability of the closed-loop system. The controller design is deduced using a backstepping transformation and constructing a Lyapunov functional. We offer global stability guaranteed by the assumption of the propagation speed is continuously differentiable and positive. The validity of the proposed controller is illustrated by a simulation result. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Stacking-Based Attention Temporal Convolutional Network for Action Segmentation 48

Stacking-Based Attention Temporal Convolutional Network for ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Liu Jiang, Yu Hong, Junkun Wu, Zhenjie Yang, Zhan Long, Jun Central South University School of Computer Science and Engineering China Central South University Big Data Institute Central South University China Central South University Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province Changsha China

ISBN: (纸本)9781728163277

Action segmentation plays an important role in video understanding, which is implemented by frame-wise action classification. Recent works on action segmentation capture long-term dependencies by increasing temporal convolution layers in Temporal Convolution Networks (TCNs). However, high layers in TCNs are more coarse access to video features, resulting in the loss of fine-grained information for frame-wise action classification. To address the above issues, we propose a novel Attention-based Temporal Convolution (ATC) block to capture fine-grained information of temporal dependencies for frame-wise action classification by self-attention mechanism. Via stacking ATC blocks, we design a Stacking-based Attention Temporal Convolutional Network (SATC) to adaptively capture long-term and short-term dependencies, according to the semantic similarity of features on different temporal receptive fields simultaneously. The experimental results demonstrate that our SATC outperforms other baselines on all three challenging datasets: GTEA, 50Salads and Breakfast. © 2023 IEEE.

关键词： Convolution

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：