检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jia, Xiaojun Zhang, Yong Wei, Xingxing Wu, Baoyuan Ma, Ke Wang, Jue Cao, Xiaochun SKLOIS Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Tencent AI Lab Shenzhen China Institute of Artificial Intelligence Beihang University Beijing China School of Data Science Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Computer Science and Technology UCAS Beijing China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen518107 China

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e., the robust accuracy against adversarial attacks suddenly and dramatically decreases. Though several FAT variants spare no effort to prevent overfitting, they sacrifice much calculation cost. In this paper, we explore the difference between the training processes of SAT and FAT and observe that the attack success rate of adversarial examples (AEs) of FAT gets worse gradually in the late training stage, resulting in overfitting. The AEs are generated by the fast gradient sign method (FGSM) with a zero or random initialization. Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process. The initialization is formed by leveraging historically generated AEs without additional calculation cost. We further provide a theoretical analysis for the proposed initialization method. We also propose a simple yet effective regularizer based on the prior-guided initialization, i.e., the currently generated perturbation should not deviate too much from the prior-guided initialization. The regularizer adopts both historical and current adversarial perturbations to guide the model learning. Evaluations on four datasets demonstrate that the proposed method can prevent catastrophic overfitting and outperform state-of-the-art FAT methods. The code is released at https://***/jiaxiaojunQAQ/FGSM-PGI. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AgFlow: Fast model selection of penalized PCA via implicit regularization effects of Gradient Flow

arXiv

引用

arXiv 2021年

作者： Jiang, Haiyan Xiong, Haoyi Wu, Dongrui Liu, Ji Dou, Dejing Big Data Lab Baidu Research School of Artificial Intelligence and Automation Huazhong University of Science and Technology

Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction. In the High Dimension Low Sample Size (HDLSS) setting, one may prefer modified principal components, with penalized loadings, and automated penalty selection by implementing model selection among these different models with varying penalties. The earlier work [1, 2] has proposed penalized PCA, indicating the feasibility of model selection in l2-penalized PCA through the solution path of Ridge regression, however, it is extremely time-consuming because of the intensive calculation of matrix inverse. In this paper, we propose a fast model selection method for penalized PCA, named Approximated Gradient Flow (AgFlow), which lowers the computation complexity through incorporating the implicit regularization effect introduced by (stochastic) gradient flow [3, 4] and obtains the complete solution path of l2-penalized PCA under varying l2-regularization. We perform extensive experiments on real-world datasets. AgFlow outperforms existing methods (Oja [5], Power [6], and Shamir [7] and the vanilla Ridge estimators) in terms of computation costs. Copyright © 2021, The Authors. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video

arXiv

引用

arXiv 2023年

作者： Xu, Zenan Meng, Xiaojun Wang, Yasheng Su, Qinliang Qiu, Zexuan Jiang, Xin Liu, Qun School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Noah’s Ark Lab Huawei Technologie The Chinese University of Hong Kong Hong Kong Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Multimodal abstractive summarization for videos (MAS) requires generating a concise textual summary to describe the highlights of a video according to multimodal resources, in our case, the video content and its transcript. Inspired by the success of the large-scale generative pre-trained language model (GPLM) in generating high-quality textual content (e.g., summary), recent MAS methods have proposed to adapt the GPLM to this task by equipping it with the visual information, which is often obtained through a general-purpose visual feature extractor. However, the generally extracted visual features may overlook some summary-worthy visual information, which impedes model performance. In this work, we propose a novel approach to learning the summary-worthy visual representation that facilitates abstractive summarization. Our method exploits the summary-worthy information from both the cross-modal transcript data and the knowledge that distills from the pseudo summary. Extensive experiments on three public multimodal datasets show that our method outperforms all competing baselines. Furthermore, with the advantages of summary-worthy visual information, our model can have a significant improvement on small datasets or even datasets with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Tail Quantile Estimation for Non-preemptive Priority Queues

arXiv

引用

arXiv 2022年

作者： Guang, Jin Hong, Guiyu Chen, Xinyun Peng, Xi Chen, Li Bai, Bo Zhang, Gong Shenzhen Research Institute of Big Data Guangdong518172 China School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China Theory Lab Central Research Institute 2012 Labs Huawei Technologies Co. Ltd Hong Kong

Motivated by applications in computing and telecommunication systems, we investigate the problem of estimating p-quantile of steady-state sojourn times in a single-server multi-class queueing system with non-preemptive priorities for p close to 1. The main challenge in this problem lies in efficient sampling from the tail event. To address this issue, we develop a regenerative simulation algorithm with importance sampling. In addition, we establish a central limit theorem for the estimator to construct the confidence interval. Numerical experiments show that our algorithm outperforms benchmark simulation methods. Our result contributes to the literature on rare event simulation for queueing systems. Copyright © 2022, The Authors. All rights reserved.

关键词： Importance sampling

来源：评论

学校读者我要写书评

暂无评论

LOPO: An Out-of-order Layer Pulling Orchestration Strategy for Fast Microservice Startup

LOPO: An Out-of-order Layer Pulling Orchestration Strategy f...

引用

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

作者： Lin Gu Junhao Huang Shaoxing Huang Deze Zeng Bo Li Hai Jin 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 Technology Huazhong University of Science and Technology Wuhan China School of Computer Science China University of Geosciences Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Container based microservices have been widely applied to promote the cloud elasticity. The mainstream Docker containers are structured in layers, which are organized in stack with bottom-up dependency. To start a microservice, the required layers are pulled from a remote registry and stored on its host server, following the layer dependency order. This incurs long microservice startup time and hinders the performance efficiency. In this paper, we discover that, for the first time, the layer pulling order can be adjusted to accelerate the microservice startup. Specifically, we address the problem on microservice layer pulling orchestration for startup time minimization and prove it as NP-hard. We propose a Longest-chain based Out-of-order layer Pulling Orchestration (LOPO) strategy with low computational complexity and guaranteed approximation ratio. Through extensive real-world trace driven experiments, we verify the efficiency of our LOPO and demonstrate that it reduces the microservice startup time by 22.71% on average in comparison with state-of-the-art solutions.

关键词：

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

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

引用

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

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li 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 Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

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 ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ 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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting

CIRI: Curricular Inactivation for Residue-aware One-shot Vid...

引用

International Conference on Computer Vision (ICCV)

作者： Weiying Zheng Cheng Xu Xuemiao Xu Wenxi Liu Shengfeng He South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Fuzhou University Singapore Management University

Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated first frame is provided. A naive solution is to propagate the initial target to the other frames with techniques like object tracking. In this context, the main obstacles are the unreliable propagation and the partially inpainted artifacts due to the inaccurate mask. For the former problem, we propose curricular inactivation to replace the hard masking mechanism for indicating the in-painting target, which is robust to erroneous predictions in long-term video inpainting. For the latter, we explore the properties of inpainting residue and present an online residue removal method in an iterative detect-and-refine manner. Extensive experiments on several real-world datasets demonstrate the quantitative and qualitative superiorities of our proposed method in one-shot video inpainting. More importantly, our method is extremely flexible that can be integrated with arbitrary traditional inpainting models, activating them to perform the reliable one-shot video inpainting task. Video demonstrations can be found in our supplement, and our code can be found at https://***/Arise-zwy/CIRI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unifying and Improving Graph Convolutional Neural Networks with Wavelet Denoising Filters 23

Unifying and Improving Graph Convolutional Neural Networks w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Li, Xiaona Han, Huijin Yan, Xiaoran Sun, Lu Ning, Zhaolong Xia, Feng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Graph convolutional neural network (GCN) is a powerful deep learning framework for network data. However, variants of graph neural architectures can lead to drastically different performance on different tasks. Model comparison calls for a unifying framework with interpretability and principled experimental procedures. Based on the theories from graph signal processing (GSP), we show that GCN's capability is fundamentally limited by the uncertainty principle, and wavelets provide a controllable trade-off between local and global information. We adapt wavelet denoising filters to the graph domain, unifying popular variants of GCN under a common interpretable mathematical framework. Furthermore, we propose WaveThresh and WaveShrink which are novel GCN models based on proven denoising filters from the signal processing literature. Empirically, we evaluate our models and other popular GCNs under a more principled procedure and analyze how trade-offs between local and global graph signals can lead to better performance in different datasets. © 2023 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Hyperbit: A Financial Temporal Knowledge Graph data Storage System

SSRN

引用

SSRN 2022年

作者： Yuan, Pingpeng Han, Sheng Zang, Shaoqi Shi, Xuanhua Jin, Hai 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 Technology Huazhong University of Science and Technology Wuhan430074 China

In the field of finance, data has the characteristics of temporal multi-frequency and heterogeneous high dimension, and the traditional knowledge graph is not suitable to express the temporal relation of financial data, so the financial temporal knowledge graph has become a research hotspot recently. There are a large number of temporal edges in the financial temporal knowledge graph. The use of general graph database management system to store financial knowledge graph data has problems such as large storage scale and slow update speed, and it cannot realize the traceability of financial data, so it cannot meet the needs of the financial field. In order to solve these problems, HyperBit, a storage system for efficient storage and management of financial data, is designed and implemented. Firstly, a temporal quad storage structure is proposed. Secondly, the Log Structured Cumulative Update (LSCU) is proposed to update financial temporal data efficiently. The update log module is designed in the system. When there is data to update, it is not directly updated in the data storage of the system, but recorded in the update log, and the system updates the content of the update log cumulatively. The system manages update logs by partition and chunk, which makes the log storage compact and independent. Besides, it is convenient for parallel processing and it improves the data update speed. Thirdly, a Bidirectional Backtracking by Final and Optimal Root (BBFOR) method is proposed to meet the requirements of efficient traceability of financial data. Unlike traditional version tracing method, BBFOR adopt both the snapshot and incremental methods which balance the space and time cost of version switching, and BBROF consider the version of the access frequency characteristic and set up the final root and the optimal root. Besides, BBROF adopt bidirectional backtracking technology to improve the efficiency of the version switching. Experimental results show that the storage cost

关键词： Switching

来源：评论

学校读者我要写书评

暂无评论

Peer is Your Pillar: A data-unbalanced Conditional GANs for Few-shot Image Generation

arXiv

引用

arXiv 2023年

作者： Li, Ziqiang Wang, Chaoyue Rui, Xue Xue, Chao Leng, Jiaxu Li, Bin Big Data and Decision Lab University of Science and Technology of China China The University of Sydney Australia JD Explore Academic China School of computer science Chongqing University of Posts and Telecommunications China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System China

Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate images that closely resemble the training data while Transfer Learning (TL) methods try to improve performance by leveraging prior knowledge from GANs pre-trained on large-scale datasets. However, current TL methods may not allow for sufficient control over the degree of knowledge preservation from the source model, making them unsuitable for setups where the source and target domains are not closely related. To address this, we propose a novel pipeline called Peer is your Pillar (PIP), which combines a target few-shot dataset with a peer dataset to create a data-unbalanced conditional generation. Our approach includes a class embedding method that separates the class space from the latent space, and we use a direction loss based on pre-trained CLIP to improve image diversity. Experiments on various few-shot datasets demonstrate the advancement of the proposed PIP, especially reduces the training requirements of few-shot image generation. © 2023, CC BY.

关键词： Large dataset

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：