中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data

文献类型：期刊论文

作者Cao, Yukun4,5; Feng, Yuan4,5; Wang, Hairu4,5; Xie, Xike3,5; Zhou, S. Kevin1,2,6
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2024-11-01
卷号46期号:11页码:7136-7153
关键词sketches meta-learning Neural data structure memory-augmented neural networks memory-augmented neural networks meta-learning memory-augmented neural networks
ISSN号0162-8828
DOI10.1109/TPAMI.2024.3388589
英文摘要Recently, there has been a trend of designing neural data structures to go beyond handcrafted data structures by leveraging patterns of data distributions for better accuracy and adaptivity. Sketches are widely used data structures in real-time web analysis, network monitoring, and self-driving to estimate item frequencies of data streams within limited space. However, existing sketches have not fully exploited the patterns of the data stream distributions, making it challenging to tightly couple them with neural networks that excel at memorizing pattern information. Starting from the premise, we envision a pure neural data structure as a base sketch, which we term the meta-sketch, to reinvent the base structure of conventional sketches. The meta-sketch learns basic sketching abilities from meta-tasks constituted with synthetic datasets following Zipf distributions in the pre-training phase and can be quickly adapted to real (skewed) distributions in the adaption phase. The meta-sketch not only surpasses its competitors in sketching conventional data streams but also holds good potential in supporting more complex streaming data, such as multimedia and graph stream scenarios. Extensive experiments demonstrate the superiority of the meta-sketch and offer insights into its working mechanism.
资助项目National Natural Science Foundation of China[61772492] ; National Natural Science Foundation of China[62072428] ; National Natural Science Foundation of China[62271465] ; Open Fund Project of Guangdong Academy of Medical Sciences, China[YKY-KF202206] ; Suzhou Basic Research Program[SYG202338]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001329047900010
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/39527]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xie, Xike; Zhou, S. Kevin
作者单位1.Univ Sci & Technol China, Suzhou Inst Adv Res, Ctr Med Imaging Robot Analyt Comp & Learning MIRAC, Hefei 230026, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
3.Univ Sci & Technol China, Sch Biomed Engn, Hefei 230026, Peoples R China
4.Univ Sci & Technol China USTC, Sch Comp Sci & Technol, Hefei 230026, Peoples R China
5.Univ Sci & Technol China, Suzhou Inst Adv Res, Ctr Med Imaging Robot Analyt Comp & Learning MIR A, Data Darkness Lab DDL, Hefei 230026, Peoples R China
6.Univ Sci & Technol China, Sch Biomed Engn, Div Life Sci & Med, Hefei 230026, Peoples R China
推荐引用方式
GB/T 7714		 Cao, Yukun,Feng, Yuan,Wang, Hairu,et al. Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,46(11):7136-7153.
APA Cao, Yukun,Feng, Yuan,Wang, Hairu,Xie, Xike,&Zhou, S. Kevin.(2024).Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,46(11),7136-7153.
MLA Cao, Yukun,et al."Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46.11(2024):7136-7153.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。