III: Medium: Collaborative Research: An Extensible Heterogeneous Network Embedding Framework with Application Specific Adaptation
III:媒介:协作研究:具有特定应用适应能力的可扩展异构网络嵌入框架
基本信息
- 批准号:2152038
- 负责人:
- 金额:$ 55万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2021
- 资助国家:美国
- 起止时间:2021-08-15 至 2024-07-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Network data is ubiquitous in the real-world, and many online websites providing various kinds services can all be represented as networks, e.g., online social networks, e-commerce networks, and academic networks. Learning and mining of network structured data have been one of the most popular yet challenging research problems studied in recent years. This project will study the problem of how to find a simple, yet effective representation for each network node, which can capture its characteristics or role in the network based on its connections. This is referred to as the network embedding problem. As an effective tool to transform network data into classic feature-vector representations, network embedding aims at mapping the network data into a low-dimensional feature space, i.e., with a small number of features for each network node. With the embedding results, all these aforementioned networks will be benefited to improve their services provided for the public. This project focuses on developing a general network embedding framework, and investigating its extension to application-oriented, multi-network and dynamic-network scenarios. This project will help support female and minority students to participate in academic research about network embedding. Network embedding studied in this project is a challenging learning task due to many reasons. (1) Data perspective, the heterogeneity of real-world social network data renders existing homogeneous-network oriented embedding models failing to work; (2) Structure preserving perspective, many first-order proximity based embedding methods can hardly preserve the complex social network structure with heterogeneous node types; and (3) Task perspective, the detachment of embedding process with external tasks makes the learnt results ineffective for application tasks with specific objectives. This project aims at tackling these challenges by proposing a novel extensible heterogeneous social network embedding model, which can effectively incorporate the objectives of external tasks in the learning process. This project covers five main themes: (1) extensible heterogeneous network embedding foundation; (2) application oriented embedding of single heterogeneous network; (3) embedding over multiple heterogeneous network for network alignment; (4) dynamic heterogeneous network embedding for friend recommendation; and (5) advanced scalable heterogeneous network embedding technique exploration. This project will greatly enrich the fundamental principles and technologies of social network mining and data mining. In terms of the broader impact, advances in network embedding analysis have transformative potential for fundamental advances in understanding the behavior and activities of the social networks.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
网络数据在现实世界中无处不在,许多提供各种服务的在线网站都可以表示为网络,例如在线社交网络、电子商务网络和学术网络。网络结构数据的学习和挖掘是近年来研究的热点问题之一,也是具有挑战性的研究课题之一。该项目将研究如何为每个网络节点找到一个简单而有效的表示,该表示能够基于其连接来捕捉其在网络中的特征或角色。这被称为网络嵌入问题。网络嵌入是将网络数据转换为经典特征向量表示的有效工具,其目的是将网络数据映射到低维特征空间,即每个网络节点具有较少的特征。有了嵌入的结果,所有上述网络都将受益于改善为公众提供的服务。本项目致力于开发一个通用的网络嵌入框架,并研究其对面向应用、多网络和动态网络场景的扩展。该项目将帮助支持女性和少数民族学生参与关于网络嵌入的学术研究。由于多种原因,本课题研究的网络嵌入是一项具有挑战性的学习任务。(1)数据视角,现实社会网络数据的异构性使得现有的面向同质网络的嵌入模型无法工作;(2)结构保持视角,许多基于一阶邻近度的嵌入方法很难保持复杂的社会网络结构和异质节点类型;(3)任务视角,嵌入过程与外部任务的分离使得学习结果对于具有特定目标的应用任务无效。本项目旨在通过提出一种新颖的可扩展的异质社会网络嵌入模型来应对这些挑战,该模型能够有效地将外部任务的目标纳入学习过程。该项目包括五个主要主题:(1)可扩展的异构网嵌入基础;(2)面向应用的单一异构网嵌入;(3)多个异构网间的网络对齐嵌入;(4)面向朋友推荐的动态异构网嵌入;(5)高级可扩展的异构网嵌入技术探索。该项目将极大地丰富社交网络挖掘和数据挖掘的基本原理和技术。就更广泛的影响而言,网络嵌入分析方面的进步对理解社交网络的行为和活动具有根本性进步的变革性潜力。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Adaptive momentum with discriminative weight for neural network stochastic optimization
- DOI:10.1002/int.22854
- 发表时间:2022-09
- 期刊:
- 影响因子:7
- 作者:Jiyang Bai;Yuxiang Ren;Jiawei Zhang
- 通讯作者:Jiyang Bai;Yuxiang Ren;Jiawei Zhang
Temporal super-resolution traffic flow forecasting via continuous-time network dynamics
- DOI:10.1007/s10115-023-01887-6
- 发表时间:2023-06
- 期刊:
- 影响因子:2.7
- 作者:Yinjie Xie;Yun Xiong;Jiawei Zhang;Chao Chen;Yao Zhang;Jie Zhao;Yizhu Jiao;Jinjing Zhao
- 通讯作者:Yinjie Xie;Yun Xiong;Jiawei Zhang;Chao Chen;Yao Zhang;Jie Zhao;Yizhu Jiao;Jinjing Zhao
Measuring and sampling: A metric‐guided subgraph learning framework for graph neural network
- DOI:10.1002/int.22891
- 发表时间:2021-12
- 期刊:
- 影响因子:7
- 作者:Jiyang Bai;Yuxiang Ren;Jiawei Zhang
- 通讯作者:Jiyang Bai;Yuxiang Ren;Jiawei Zhang
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Jiawei Zhang其他文献
Designing a reductive hybrid membrane to selectively capture noble metallic ions during oil/water emulsion separation with further function enhancement
设计一种还原杂化膜,在油/水乳液分离过程中选择性捕获贵金属离子,并进一步增强功能
- DOI:
10.1039/c8ta01864b - 发表时间:
2018 - 期刊:
- 影响因子:11.9
- 作者:
Lei Zhang;Xian-Hu Zha;Gui Zhang;Jincui Gu;Wei Zhang;Youju Huang;Jiawei Zhang;Tao Chen - 通讯作者:
Tao Chen
Search for the semileptonic decay $D_s^+\to \pi^0e^+\nu_e$
搜索半轻衰变 $D_s^ o pi^0e^
u_e$
- DOI:
- 发表时间:
2022 - 期刊:
- 影响因子:0
- 作者:
B. C. M. Ablikim;M. Achasov;P. Adlarson;M. Albrecht;R. Aliberti;A. Amoroso;M. An;Q. An;X. Bai;Y. Bai;O. Bakina;R. Ferroli;I. Balossino;Y. Ban;V. Batozskaya;D. Becker;K. Begzsuren;N. Berger;M. Bertani;D. Bettoni;F. Bianchi;J. Bloms;A. Bortone;I. Boyko;R. Briere;A. Brueggemann;H. Cai;X. Cai;A. Calcaterra;G. Cao;N. Cao;S. Çetin;J. Chang;W. Chang;G. Chelkov;C. Chen;Chao Chen;G. Chen;Huifen. Chen;M. Chen;S. Chen;S. Chen;T. Chen;X. Chen;X. Chen;Y. Chen;Z. Chen;W. Cheng;X. Chu;G. Cibinetto;F. Cossio;J. Cui;H. Dai;J. Dai;A. Dbeyssi;R. Boer;D. Dedovich;Z. Deng;A. Denig;I. Denysenko;M. Destefanis;F. Mori;Y. Ding;J. Dong;L. Dong;M. Dong;X. Dong;S. Du;P. Egorov;Y. Fan;J. Fang;S. Fang;W. Fang;Y. Fang;R. Farinelli;L. Fava;F. Feldbauer;G. Felici;C. Feng;J. Feng;K. Fischer;M. Fritsch;C. Fritzsch;C. Fu;H. Gao;Y. Gao;Yan‐Yan Gao;S. Garbolino;I. Garzia;P. Ge;Z. Ge;C. Geng;E. Gersabeck;A. Gilman;K. Goetzen;L. Gong;W. Gong;W. Gradl;M. Greco;L. Gu;M. Gu;Y. Gu;C. Guan;A. Guo;L. Guo;R. Guo;Y. Guo;A. Guskov;T. Han;W. Han;X. Hao;F. Harris;K. He;K. He;F. Heinsius;C. Heinz;Y. Heng;C. Herold;M. Himmelreich;G. Hou;Y. Hou;Z. Hou;H. Hu;J. Hu;T. Hu;Y. Hu;G. Huang;K. Huang;L. Huang;X. Huang;Y. Huang;Z. Huang;T. Hussain;N. Husken;W. Imoehl;M. Irshad;J. Jackson;S. Jaeger;S. Janchiv;Q. Ji;Q. Ji;X. Ji;X. Ji;Y. Ji;Z. Jia;H. Jiang;S. Jiang;X. Jiang;Y. Jiang;J. Jiao;Z. Jiao;S. Jin;Y. Jin;M. Jing;T. Johansson;N. Kalantar;X. Kang;R. Kappert;M. Kavatsyuk;B. Ke;I. Keshk;A. Khoukaz;P. Kiese;R. Kiuchi;R. Kliemt;L. Koch;O. B. Kolcu;B. Kopf;M. Kuemmel;M. Kuessner;A. Kupsc;W. Kuhn;J. J. Lane;J. Lange;P. Larin;A. Lavania;L. Lavezzi;Z. Lei;H. Leithoff;M. Lellmann;T. Lenz;C. Li;C. Li;Cheng Li;D. Li;F. Li;G. Li;H. Li;H. Li;H. Li;H. Li;J. Li;J. Li;J. Li;Kenneth K. Li;L. Li;L. Li;Lei Li;M. Li;P. Li;S. Li;S. Li;T. Li;W. Li;W. Li;X. Li;X. Li;Xiaoyu Li;Z. Li;H. Liang;Y. Liang;Y. Liang;G. Liao;L. Liao;J. Libby;A. Limphirat;C. Lin;D. Lin;T. Lin;B. Liu;C. Liu;D. Liu;F. Liu;F. Liu;Feng. Liu;G. Liu;H. Liu;H. Liu;H. Liu;Huanhuan Liu;Huihui Liu;J. Liu;J. Liu;J. Liu;Li;Li;Li;Li;Lusheng Liu;M. Liu;Li;Q. Liu;S. Liu;T. Liu;W. Liu;W. Liu;X. Liu;Y. Liu;Y. Liu;Z. Liu;Z. Liu;X. Lou;F. Lu;H. Lu;J. Lu;X. Lu;Y. Lu;Y. Lu;Z. Lu;C. L. Luo;M. Luo;T. Luo;X. Luo;X. Lyu;Y. Lyu;F. Ma;H. Ma;Li Ma;M. Ma;Q. Ma;R. Ma;R. Ma;X. Ma;Y. Ma;F. Maas;M. Maggiora;S. Maldaner;S. Malde;Q. A. Malik;A. Mangoni;Y. Mao;Z. Mao;S. Marcello;Z. Meng;J. Messchendorp;G. Mezzadri;H. Miao;T. Min;R. Mitchell;X. Mo;N. Muchnoi;Y. Nefedov;F. Nerling;I. Nikolaev;Z. Ning;S. Nisar;Y. Niu;S. L. Olsen;Q. Ouyang;S. Pacetti;X. Pan;Y. Pan;A. Pathak;M. Pelizaeus;H. Peng;K. Peters;J. Ping;R. Ping;S. Plura;S. Pogodin;V. Prasad;F. Qi;H. Qi;H. Qi;M. Qi;T. Qi;S. Qian;W. B. Qian;Z. Qian;C. Qiao;J. Qin;L. Qin;X. Qin;X. Qin;Z. Qin;J. Qiu;S. Qu;K. H. Rashid;C. Redmer;K. Ren;A. Rivetti;V. Rodin;M. Rolo;G. Rong;C. Rosner;S. Ruan;H. Sang;A. Sarantsev;Y. Schelhaas;C. Schnier;K. Schoenning;M. Scodeggio;K. Shan;W. Shan;X. Shan;J. Shangguan;L. Shao;M. Shao;C. Shen;H. Shen;X. Shen;B. Shi;H. Shi;J. Shi;Q. Shi;R. Shi;X. Shi;X. Shi;J. Song;W. Song;Y. Song;S. Sosio;S. Spataro;F. Stieler;K. Su;P. Su;Y. Su;G. Sun;H. Sun;H. Sun;J. Sun;L. Sun;S. Sun;T. Sun;W. Sun;X. Sun;Y. Sun;Y. Sun;Z. Sun;Y. Tan;Y. Tan;C. Tang;G. Tang;J. Tang;L. Tao;Q. Tao;M. Tat;J. Teng;V. Thorén;W. Tian;Y. Tian;I. Uman;B. Wang;B. Wang;C. Wang;D. Wang;F. Wang;H. Wang;H. Wang;K. Wang;L. Wang;M. Wang;M. Wang;Meng Wang;S. Wang;T. Wang;T. Wang;W. Wang;W. Wang;W. Wang;X. Wang;X. Wang;X. L. Wang;Yu Wang;Y. Wang;Y. Wang;Y. Wang;Y. Wang;Yaqian Wang;Z. Wang;Z. Wang;Ziyi Wang;D. Wei;F. Weidner;S. Wen;D. White;U. Wiedner;G. Wilkinson;M. Wolke;L. Wollenberg;J. Wu;L. Wu;L. Wu;X. Wu;X. Wu;Y. Wu;Y. Wu;Z. Wu;L. Xia;T. Xiang;D. Xiao;G. Xiao;H. Xiao;S. Xiao;Y. Xiao;Z. Xiao;C. Xie;X. Xie;Y. Xie;Y. Xie;Y. Xie;Z. Xie;T. Xing;C. Xu;C. Xu;G. Xu;H. Xu;Q. Xu;X. Xu;Y. Xu;Z. Xu;F. Yan;L. Yan;W. Yan;W. Yan;H. Yang;H. Yang;Hang Yang;L. Yang;S. Yang;T. Yang;Y. Yang;Y. Yang;Yifan Yang;M. Ye;M. Ye;J. Yin;Z. You;B. Yu;C. Yu;G. Yu;T. Yu;C. Yuan;Lijuan Yuan;S. Yuan;X. Yuan;Y. Yuan;Z. Yuan;C. Yue;A. Zafar;F. Zeng;X. Zeng;Y. Zeng;Y. Zhan;A. Zhang;B. L. Zhang;B. Zhang;D. Zhang;G. Zhang;Houyu Zhang;Houyu Zhang;H. Zhang;J. Zhang;J. Zhang;J. Zhang;J. X. Zhang;J. Zhang;J. Zhang;Jianyu Zhang;Jiawei Zhang;L. Zhang;L. Zhang;Lei. Zhang;P. Zhang;Q. Zhang;Shuihan Zhang;Shulei Zhang;X. Zhang;X. Zhang;X. Zhang;Y. Zhang;Y. Zhang;Y. Zhang;Yan Zhang;Yao Zhang;Z. Zhang;Z. Zhang;G. Zhao;J. Zhao;J. Zhao;J. Zhao;Lei Zhao;Ling Zhao;M. Zhao;Q. Zhao;S. Zhao;Y. Zhao;Y. Zhao;Z. Zhao;A. Zhemchugov;B. Zheng;J. Zheng;Y. Zheng;B. Zhong;C. Zhong;X. Zhong;H. Zhou;L. Zhou;X. Zhou;X. Zhou;X. Zhou;X. Zhou;Yanlin Zhou;J. Zhu;K. Zhu;K. Zhu;L. Zhu;S. Zhu;S. Zhu;T. Zhu;W. Zhu;Y. Zhu;Z. Zhu;B. Zou;J. Zou - 通讯作者:
J. Zou
Methoxylation and Direct Hydrogenative Coupling of Chloronitrobenzenes in Continuous Flow
连续流中氯硝基苯的甲氧基化和直接氢化偶联
- DOI:
10.1002/cjoc.201600606 - 发表时间:
2017-04 - 期刊:
- 影响因子:0
- 作者:
Songjie Shi;Li Wan;Xiaoning Sun;Jiawei Zhang;Kai Guo - 通讯作者:
Kai Guo
Uncertainty-aware multidimensional ensemble data visualization and exploration
不确定性感知多维集成数据可视化和探索
- DOI:
10.1109/tvcg.2015.2410278 - 发表时间:
2015 - 期刊:
- 影响因子:5.2
- 作者:
Haidong Chen;Song Zhang;Wei Chen;Honghui Mei;Jiawei Zhang;Andrew Mercer;Ronghua Liang;Huamin Qu - 通讯作者:
Huamin Qu
G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
- DOI:
- 发表时间:
2020-06 - 期刊:
- 影响因子:0
- 作者:
Jiawei Zhang - 通讯作者:
Jiawei Zhang
Jiawei Zhang的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Jiawei Zhang', 18)}}的其他基金
III: Medium: Collaborative Research: Self-Supervised Recommender System Learning with Application Specific Adaption
III:媒介:协作研究:具有特定应用适应性的自监督推荐系统学习
- 批准号:
2106972 - 财政年份:2021
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
III: Medium: Collaborative Research: Self-Supervised Recommender System Learning with Application Specific Adaption
III:媒介:协作研究:具有特定应用适应性的自监督推荐系统学习
- 批准号:
2202161 - 财政年份:2021
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
III: Medium: Collaborative Research: An Extensible Heterogeneous Network Embedding Framework with Application Specific Adaptation
III:媒介:协作研究:具有特定应用适应能力的可扩展异构网络嵌入框架
- 批准号:
1763365 - 财政年份:2018
- 资助金额:
$ 55万 - 项目类别:
Continuing Grant
Collaborative Research: Optimization Approach to Collaborative Games in Supply Chain Management
协作研究:供应链管理中协作博弈的优化方法
- 批准号:
0654116 - 财政年份:2007
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
相似海外基金
III : Medium: Collaborative Research: From Open Data to Open Data Curation
III:媒介:协作研究:从开放数据到开放数据管理
- 批准号:
2420691 - 财政年份:2024
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: III: Medium: Designing AI Systems with Steerable Long-Term Dynamics
合作研究:III:中:设计具有可操纵长期动态的人工智能系统
- 批准号:
2312865 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: III: MEDIUM: Responsible Design and Validation of Algorithmic Rankers
合作研究:III:媒介:算法排序器的负责任设计和验证
- 批准号:
2312932 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: III: Medium: Algorithms for scalable inference and phylodynamic analysis of tumor haplotypes using low-coverage single cell sequencing data
合作研究:III:中:使用低覆盖率单细胞测序数据对肿瘤单倍型进行可扩展推理和系统动力学分析的算法
- 批准号:
2415562 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
III: Medium: Collaborative Research: Integrating Large-Scale Machine Learning and Edge Computing for Collaborative Autonomous Vehicles
III:媒介:协作研究:集成大规模机器学习和边缘计算以实现协作自动驾驶汽车
- 批准号:
2348169 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Continuing Grant
Collaborative Research: III: Medium: VirtualLab: Integrating Deep Graph Learning and Causal Inference for Multi-Agent Dynamical Systems
协作研究:III:媒介:VirtualLab:集成多智能体动态系统的深度图学习和因果推理
- 批准号:
2312501 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: III: Medium: Knowledge discovery from highly heterogeneous, sparse and private data in biomedical informatics
合作研究:III:中:生物医学信息学中高度异构、稀疏和私有数据的知识发现
- 批准号:
2312862 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: III: MEDIUM: Responsible Design and Validation of Algorithmic Rankers
合作研究:III:媒介:算法排序器的负责任设计和验证
- 批准号:
2312930 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: III: Medium: New Machine Learning Empowered Nanoinformatics System for Advancing Nanomaterial Design
合作研究:III:媒介:新的机器学习赋能纳米信息学系统,促进纳米材料设计
- 批准号:
2347592 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant
Collaborative Research: IIS: III: MEDIUM: Learning Protein-ish: Foundational Insight on Protein Language Models for Better Understanding, Democratized Access, and Discovery
协作研究:IIS:III:中等:学习蛋白质:对蛋白质语言模型的基础洞察,以更好地理解、民主化访问和发现
- 批准号:
2310113 - 财政年份:2023
- 资助金额:
$ 55万 - 项目类别:
Standard Grant