检索结果-内蒙古大学图书馆

Latest Technologies on dataset Distillation: A Survey

Procedia Computer Science 2024年 242卷 1112-1117页

作者： Muyang Li Yi Qu Yong Shi Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA

dataset distillation refers to the process of constructing a smaller dataset based on a larger dataset, so that the training model with the smaller dataset can obtain similar results to the larger dataset. In this paper, we first briefly review the basic methods and some recent advances in this field from the perspectives of meta-learning framework and data matching framework, including the backpropagation through time(BPTT), kernel ridge regression(KRR), decoupled techniques, gradient matching(DC), trajectory matching(MTT) and distribution matching(DM). The results of the plug-and-play approach in recent years are then presented. Finally, we discuss possible future developments from the perspectives of data distillation algorithms on large datasets, the relationship between compress ratio and information contained, more tasks and data modalities, and the use of generative models to improve the distillation results of datasets.

关键词： dataset Distillation Survey Meta-learning framework data matching framework

来源：评论

学校读者我要写书评

暂无评论

Quaternion Ordinal Embedding 31

Quaternion Ordinal Embedding

引用

31st International Joint Conference on Artificial Intelligence (IJCAI)

作者： Hou, Wenzheng Xu, Qianqian Ma, Ke Hao, Qianxiu Huang, Qingming Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Peng Cheng Lab Artificial Intelligence Res Ctr Shenzhen Peoples R China

ISBN: (纸本)9781956792003

Ordinal embedding (OE) aims to project objects into a low-dimensional space while preserving their ordinal constraints as well as possible. Generally speaking, a reasonable OE algorithm should simultaneously capture a) semantic meaning and b) the ordinal relationship of the objects. However, most of the existing methods merely focus on b). To address this issue, our goal in this paper is to seek a generic OE method to embrace the two features simultaneously. We argue that different dimensions of vector-based embedding are naturally entangled with each other. To realize a), we expect to decompose the D dimensional embedding space into D different semantic subspaces, where each subspace is associated with a matrix representation. Unfortunately, introducing a matrix-based representation requires far more complex parametric space than its vector-based counterparts. Thanks to the algebraic property of quaternions, we are able to find a more efficient way to represent a matrix with quaternions. For b), inspired by the classic chordal Grassmannian distance, a new distance function is defined to measure the distance between different quaternions/matrices, on top of which we construct a generic OE loss function. Experimental results for different tasks on both simulated and real-world datasets verify the effectiveness of our proposed method.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

MaxMatch: Semi-Supervised Learning With Worst-Case Consistency

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第5期45卷 5970-5987页

作者： Jiang, Yangbangyan Li, Xiaodan Chen, Yuefeng He, Yuan Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Alibaba Grp Secur Dept Hangzhou 311121 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Sun Yat Sen Univ Sch Cyber Sci & Technol Shenzhen Campus Shenzhen 518107 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management BDKM Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-art models are based on the idea of pursuing consistent model predictions over unlabeled data toward the input noise, which is called consistency regularization. Nonetheless, there is a lack of theoretical insights into the reason behind its success. To bridge the gap between theoretical and practical results, we propose a worst-case consistency regularization technique for SSL in this article. Specifically, we first present a generalization bound for SSL consisting of the empirical loss terms observed on labeled and unlabeled training data separately. Motivated by this bound, we derive an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants. We then provide a simple but effective algorithm to solve the proposed minimax problem, and theoretically prove that it converges to a stationary point. Experiments on five popular benchmark datasets validate the effectiveness of our proposed method.

关键词： Predictive models Training data models Semantics Perturbation methods Computational modeling Benchmark testing Semi-supervised learning consistency regularization worst-case consistency image classification

来源：评论

学校读者我要写书评

暂无评论

Impact of Consumer Perceived Characteristics on Fruit Sales: Evidence from Community Group-buying

引用

Procedia Computer Science 2024年 242卷 662-668页

作者： Hailiang Jiang Xin Tian Ye Tao Lulu Wang Research Center on Fictitious Economy and Data Science. Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Beijing HAOLINJU CVS Co. Ltd Beijing 100088 China Shanghai HEADING Information Engineering Co. Ltd. Shanghai 201112 China

There is a growing trend among retailers to sell fruits through their community group-buying (CGB) channels. Based on real operational data, we employ econometric models to empirically analyze how consumer perception characteristics in CGB affect fruit sales. Our findings suggest that incorporating subjective experiences into product descriptions can positively impact fruit sales for retailers; fresh produce stores outperform regular stores in fruit sales of CGB; Dark-colored fruits sell more than light-colored fruits in the CGB channel. Our study offers valuable insights for retailers selling fruits through CGB channels.

关键词： community group-buying subjectivity fresh produce stores dark-colored fruits

来源：评论

学校读者我要写书评

暂无评论

D4M: dataset Distillation via Disentangled Diffusion Model

D4M: Dataset Distillation via Disentangled Diffusion Model

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Duo Su Junjie Hou Weizhi Gao Yingjie Tian Bowen Tang UCAS School of Computer Science and Technology Research Center on Fictitious Economy and Data Science CAS Key Laboratory of Big Data Mining and Knowledge Management CAS UCAS Sino-Danish College Department of Computer Science NCSU UCAS School of Economics and Management UCAS MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation CAS Institute of Computing Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce dataset Distillation via Disentangled Diffusion Model (D 4 M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D 4 M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects.

关键词： Training Computer vision Computational modeling Prototypes Computer architecture Diffusion models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Decoupled graph knowledge distillation: A general logits-based method for learning MLPs on graphs

引用

NEURAL NETWORKS 2024年 179卷 106567页

作者： Tian, Yingjie Xu, Shaokai Li, Muyang Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

While Graph Neural Networks (GNNs) have demonstrated their effectiveness in processing non-Euclidean structured data, the neighborhood fetching of GNNs is time-consuming and computationally intensive, making them difficult to deploy in low-latency industrial applications. To address the issue, a feasible solution is graph knowledge distillation (KD), which can learn high-performance student Multi-layer Perceptrons (MLPs) to replace GNNs by mimicking the superior output of teacher GNNs. However, state-of-the-art graph knowledge distillation methods are mainly based on distilling deep features from intermediate hidden layers, this leads to the significance of logit layer distillation being greatly overlooked. To provide a novel viewpoint for studying logits-based KD methods, we introduce the idea of decoupling into graph knowledge distillation. Specifically, we first reformulate the classical graph knowledge distillation loss into two parts, i.e., the target class graph distillation (TCGD) loss and the non-target class graph distillation (NCGD) loss. Next, we decouple the negative correlation between GNN's prediction confidence and NCGD loss, as well as eliminate the fixed weight between TCGD and NCGD. We named this logits-based method Decoupled Graph knowledge Distillation (DGKD). It can flexibly adjust the weights of TCGD and NCGD for different data samples, thereby improving the prediction accuracy of the student MLP. Extensive experiments conducted on public benchmark datasets show the effectiveness of our method. Additionally, DGKD can be incorporated into any existing graph knowledge distillation framework as a plug-and-play loss function, further improving distillation performance. The code is available at https://***/xsk160/DGKD.

关键词： Graph knowledge distillation Decoupling Graph neural networks Multi-layer perceptrons

来源：评论

学校读者我要写书评

暂无评论

Syntax-Guided Hierarchical Attention Network for Video Captioning

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第2期32卷 880-892页

作者： Deng, Jincan Li, Liang Zhang, Beichen Wang, Shuhui Zha, Zhengjun Huang, Qingming Chinese Acad Sci Key Lab Intelligent Informat Proc CAS Beijing 100190 Peoples R China Chinese Acad Sci Inst Comp Technol CAS Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp & Control Engn Beijing 101408 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 101408 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230027 Peoples R China

Video captioning is a challenging task that aims to generate linguistic description based on video content. Most methods only incorporate visual features (2D/3D) as input for generating visual and non-visual words in the caption. However, generating non-visual words usually depends more on sentence-context than visual features. The wrong non-visual words can reduce the sentence fluency and even change the meaning of sentence. In this paper, we propose a syntax-guided hierarchical attention network (SHAN), which leverages semantic and syntax cues to integrate visual and sentence-context features for captioning. First, a globally-dependent context encoder is designed to extract the global sentence-context feature that facilitates generating non-visual words. Then, we introduce hierarchical content attention and syntax attention to adaptively integrate features in terms of temporality and feature characteristics respectively. Content attention helps focus on time intervals related to the semantic of current word, while cross-modal syntax attention uses syntax information to model importance of different features for target word's generation. Moreover, such hierarchical attention can enhance the model interpretability for captioning. Experiments on MSVD and MSR-VTT datasets show the comparable performance of our method compared with current methods.

关键词： Syntactics Feature extraction Visualization Generators Semantics Two dimensional displays Three-dimensional displays Video captioning syntax attention content attention global sentence-context

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Risk Identification Based on Deep Learning Model 20th

Network Traffic Risk Identification Based on Deep Learning M...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Zhai, Weinan Liu, Siqi Yu, Yue An, Wei Yu, Jianjun Zhang, Lingling Univ Chinese Acad Sci Sch Econ & Management Beijing 100049 Peoples R China Chinese Acad Sci Inst Informat Engn Beijing 100085 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Chinese Acad Sci Comp Network Informat Ctr Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China UCAS MOE Social Sci Lab Digital Econ Forecasts & Polic Beijing 100190 Peoples R China

ISBN: (纸本)9789819756025;9789819756032

In the realm of network traffic analysis, ensuring system security requires accurate identification of risks posed by various attacks. A notable trend is attackers' exploitation of the HTTPs protocol to conceal malicious activities and evade detection. Current methods, tailored for predefined scenarios, struggle to detect unknown malicious traffic. These methods often rely solely on statistical features or raw bytes, limiting their effectiveness. Our research introduces a novel approach that seamlessly integrates raw byte information and statistical features to pinpoint camouflaged malware traffic within HTTPs flows. This approach consists of two interconnected sub-networks: PF-net, which extracts latent features from raw bytes, and RE-net, which reconstructs these features and determines an optimal threshold for accurate classification. Extensive experiments show our approach outperforms baseline methods on MTA and STRA datasets, achieving F1-scores of 0.849 and 0.935, respectively. An optimal threshold of 1.0 offers consistent performance, balancing false positives and negatives.

关键词： Network Flow Flow Risk Deep Learning Feature

来源：评论

学校读者我要写书评

暂无评论

Review of monopoly models and implications for antitrust 8

Review of monopoly models and implications for antitrust

引用

8th International Conference on Information Technology and Quantitative management (ITQM) - Developing Global Digital Economy after COVID-19

作者： Shang, Mengyu Li, Yuan Qi, Zhiquan Univ Chinese Acad Sci Beijing 100190 Peoples R China Univ Lyon MSH 14-16 Av Berthelot F-69363 Lyon France Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

In February 2021, the Ministry of Commerce Anti-monopoly Bureau of the People's Republic of China released the Antitrust Guidelines for the Platform Economy Industry. This announcement signaled more governmental supervision and governance with Internet-related business. In practice, tech giants have been suffering administrative penalties one after another. This study presents a review and analysis of the research literature on the monopoly quantitative models, outlining the components and concluding the implications for anti-monopoly. This paper delineates three main research topics relating to the monopoly models within the literature: the oligopoly, monopolistic competition, and Internet platform monopoly. The Cournot model, Bertrand model, Stackelberg model, and Innovational model represent the oligopoly studies when a small group of large sellers dominates the market. We then discuss the monopolistic competition models as the Krugman model, D-S Model, and Lancaster Model. We pay particular attention to the platform economy to reflect the new era of monopoly with Marshall's Dilemma After the summary and comparison of the literature research trajectory, our analysis culminates in implications for antitrust: why Internet corporations and government meet this monopoly predicament, who are involved by monopoly policy, how consumers and market got impacted, and what countermeasures could be taken to improve the antitrust. This study contributes to overview the development of monopoly models and critically analyze based on the current antitrust situation and trend of platform economy integration. We should scrutinize the feasibility to adopt engrain view of monopoly mechanisms as benefit loss on the information technology economy. Therefore, this research raises the novel question and synergistic effects of monopoly. (C) 2021 The Authors. Published by Elsevier B.V.

关键词： Monopoly oligopoly models antitrust platform economy

来源：评论

学校读者我要写书评

暂无评论

FedPS: A Privacy Protection Enhanced Personalized Search Framework 21

FedPS: A Privacy Protection Enhanced Personalized Search Fra...

引用

30th World Wide Web Conference (WWW)

作者： Yao, Jing Dou, Zhicheng Wen, Ji-Rong Renmin Univ China Sch Informat Beijing Peoples R China Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China MOE Key Lab Data Engn & Knowledge Engn Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

ISBN: (纸本)9781450383127

Personalized search returns each user more accurate results by collecting the user's historical search behaviors to infer her interests and query intents. However, it brings the risk of user privacy leakage, and this may greatly limit the practical application of personalized search. In this paper, we focus on the problem of privacy protection in personalized search, and propose a privacy protection enhanced personalized search framework, denoted with FedPS. Under this framework, we keep each user's private data on her individual client, and train a shared personalized ranking model with all users' decentralized data by means of federated learning. We implement two models within the framework: the first one applies a personalization model with a personal module that fits the user's data distribution to alleviate the challenge of data heterogeneity in federated learning;the second model introduces trustworthy proxies and group servers to solve the problems of limited communication, performance bottleneck and privacy attack for FedPS. Experimental results verify that our proposed framework can enhance privacy protection without losing too much accuracy.

关键词： personalized search privacy protection federated learning

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：