III: Small: Collaborative Research: Effective Labeled Data Generation via Generative Adversarial Learning
III:小:协作研究:通过生成对抗性学习有效生成标记数据
基本信息
- 批准号:1909702
- 负责人:
- 金额:$ 39.99万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2019
- 资助国家:美国
- 起止时间:2019-10-01 至 2023-09-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Recent successes in applying deep learning to solve many challenging data science problems is in part due to the availability of large-scale labeled training data. However, creating large-scale labeled datasets is time consuming, labor-intensive, costly, and often requires significant domain knowledge. Many real-world applications, therefore, come with only data with limited label information (i.e., a small amount of labeled data or no labeled data). Thus, lack of labeled training data is still one of major roadblocks in applying deep learning techniques to challenging data science problems. On the other hand, recent advancements in generative adversarial learning have shown promising results in generating realistic data, which could enable a new perspective for alleviating the problem of lacking labeled training data. Thus, this project explores effective labeled data generation via generative adversarial learning. The proposed research extends the state-of-the-art labeled data generation and generative adversarial learning to a new frontier, investigates original problems that entreat innovative solutions and paves the way for a new research endeavor effectively tame synthetic labeled data generation. As many real-world problems face the challenge of limited labeled data, the project has potential to benefit many real-world applications from various disciplines such as Computer Science, Education, Politics, Healthcare and Bioinformatics.This project proposes novel approaches based on generative adversarial learning for effective labeled data generation to facilitate deep learning with limited label information, investigates associated fundamental research issues and develops effective algorithms. It has three primary research objectives. First, when a small amount of labeled data is available, it explores to estimate the underlying data distribution from unlabeled data and incorporate the label information for labeled data generation, including extremely imbalanced data and incomplete label scenarios. Second, when labeled data is not available, it adopts an alternative weak supervision (e.g., inaccurate labels, inexact labels and pairwise constraints) for generating labeled data. Third, when neither labeled data nor weak supervision is available, it explores to integrate human involvement to generative adversarial learning for providing supervision. Disparate means are planned to disseminate the project and its findings, such as web enabled data and software repositories, books, journal and conference publications, special purpose workshops or tutorials, and industrial collaborations. The project can be effectively integrated to undergraduate and graduate courses as well as in student research projects.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.
在应用深度学习来解决许多具有挑战性的数据科学问题方面,最近取得的成功部分是由于具有大规模标记的培训数据的可用性。但是,创建大规模标记的数据集是耗时,劳动力密集,昂贵的,并且通常需要重要的领域知识。因此,许多实际应用程序仅包含具有有限标签信息的数据(即少量标记的数据或没有标记的数据)。因此,缺乏标记的培训数据仍然是将深度学习技术应用于挑战性数据科学问题的主要障碍之一。另一方面,生成对抗性学习的最新进展在生成现实数据方面显示出令人鼓舞的结果,这可以使新的观点减轻缺乏标记的培训数据的问题。因此,该项目通过生成对抗性学习探索了有效的标记数据生成。拟议的研究将最先进的标记数据生成和生成对抗性学习扩展到了新的边境,研究了原始问题,这些问题吸引了创新的解决方案,并为一项新的研究努力铺平了道路,从而有效地驯服了合成标记的数据生成。 As many real-world problems face the challenge of limited labeled data, the project has potential to benefit many real-world applications from various disciplines such as Computer Science, Education, Politics, Healthcare and Bioinformatics.This project proposes novel approaches based on generative adversarial learning for effective labeled data generation to facilitate deep learning with limited label information, investigates associated fundamental research issues and develops effective algorithms.它具有三个主要的研究目标。首先,当有少量标记的数据可用时,它将探索以估算未标记数据的基础数据分布,并将标签信息包含在标签数据生成中,包括极度不平衡的数据和不完整的标签场景。其次,当没有标记的数据可用时,它会采用替代性弱监督(例如,标签不正确,不精确标签和成对约束)来生成标记的数据。第三,当没有标记的数据或弱监督下,它会探索以将人类参与到生成的对抗性学习中以提供监督。计划分散的手段来传播该项目及其发现,例如启用Web的数据和软件存储库,书籍,期刊和会议出版物,特殊目的研讨会或教程以及工业合作。该项目可以有效地整合到本科和研究生课程以及学生研究项目中。该奖项反映了NSF的法定任务,并被认为是值得通过基金会的知识分子优点和更广泛的影响评估标准通过评估来获得支持的。
项目成果
期刊论文数量(51)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
- DOI:10.1145/3437963.3441720
- 发表时间:2021-03
- 期刊:
- 影响因子:0
- 作者:Tianxiang Zhao;Xiang Zhang;Suhang Wang
- 通讯作者:Tianxiang Zhao;Xiang Zhang;Suhang Wang
Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
- DOI:10.1145/3437963.3441752
- 发表时间:2021-01-01
- 期刊:
- 影响因子:0
- 作者:Dai, Enyan;Wang, Suhang
- 通讯作者:Wang, Suhang
Jointly Attacking Graph Neural Network and its Explanations
- DOI:10.1109/icde55515.2023.00056
- 发表时间:2021-08
- 期刊:
- 影响因子:0
- 作者:Wenqi Fan;Wei Jin;Xiaorui Liu;Han Xu;Xianfeng Tang;Suhang Wang;Qing Li;Jiliang Tang;
- 通讯作者:Wenqi Fan;Wei Jin;Xiaorui Liu;Han Xu;Xianfeng Tang;Suhang Wang;Qing Li;Jiliang Tang;
Learning fair models without sensitive attributes: A generative approach
- DOI:10.1016/j.neucom.2023.126841
- 发表时间:2023-09
- 期刊:
- 影响因子:6
- 作者:Huaisheng Zhu;Enyan Dai;Hui Liu;Suhang Wang
- 通讯作者:Huaisheng Zhu;Enyan Dai;Hui Liu;Suhang Wang
HP-GMN: Graph Memory Networks for Heterophilous Graphs
- DOI:10.1109/icdm54844.2022.00165
- 发表时间:2022-10
- 期刊:
- 影响因子:0
- 作者:Junjie Xu;Enyan Dai;Xiang Zhang;Suhang Wang
- 通讯作者:Junjie Xu;Enyan Dai;Xiang Zhang;Suhang Wang
{{
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 }}
Suhang Wang其他文献
Chapter 11 Deep Learning for Feature Representation
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
Suhang Wang - 通讯作者:
Suhang Wang
SrVARM: State Regularized Vector Autoregressive Model for Joint Learning of Hidden State Transitions and State-Dependent Inter-Variable Dependencies from Time Series Data
SrVARM:状态正则向量自回归模型,用于联合学习时间序列数据中的隐藏状态转换和状态相关的变量间依赖性
- DOI:
- 发表时间:
2021 - 期刊:
- 影响因子:0
- 作者:
Tsung;Yiwei Sun;Xianfeng Tang;Suhang Wang;Vasant G Honavar - 通讯作者:
Vasant G Honavar
Phase modulation and chemical activation of MoSe2 by phosphorus for electrocatalytic hydrogen evolution reaction
磷对MoSe2的相调制和化学活化用于电催化析氢反应
- DOI:
10.1002/ente.201901503 - 发表时间:
2020 - 期刊:
- 影响因子:3.8
- 作者:
Lunfeng Chen;Yuanmin Zhu;Jun Li;Hanghang Feng;Tingya Li;Xueyan Zhang;Suhang Wang;Meng Gu;Peixin Zhang;Chenyang Zhao - 通讯作者:
Chenyang Zhao
Randomized Feature Engineering as a Fast and Accurate Alternative to Kernel Methods
随机特征工程作为核方法的快速而准确的替代方案
- DOI:
10.1145/3097983.3098001 - 发表时间:
2017 - 期刊:
- 影响因子:0
- 作者:
Suhang Wang;C. Aggarwal;Huan Liu - 通讯作者:
Huan Liu
Enhanced low-rank representation via sparse manifold adaption for semi-supervised learning
通过半监督学习的稀疏流形适应增强低秩表示
- DOI:
10.1016/j.neunet.2015.01.001 - 发表时间:
2015-05 - 期刊:
- 影响因子:7.8
- 作者:
Yong Peng;Bao-Liang Lu;Suhang Wang - 通讯作者:
Suhang Wang
Suhang Wang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('Suhang Wang', 18)}}的其他基金
III: Medium: Collaborative Research: Towards Scalable and Interpretable Graph Neural Networks
III:媒介:协作研究:迈向可扩展和可解释的图神经网络
- 批准号:
1955851 - 财政年份:2020
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
相似国自然基金
基于超宽频技术的小微型无人系统集群协作关键技术研究与应用
- 批准号:
- 批准年份:2020
- 资助金额:57 万元
- 项目类别:面上项目
异构云小蜂窝网络中基于协作预编码的干扰协调技术研究
- 批准号:61661005
- 批准年份:2016
- 资助金额:30.0 万元
- 项目类别:地区科学基金项目
密集小基站系统中的新型接入理论与技术研究
- 批准号:61301143
- 批准年份:2013
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
ScFVCD3-9R负载Bcl-6靶向小干扰RNA治疗EAMG的试验研究
- 批准号:81072465
- 批准年份:2010
- 资助金额:31.0 万元
- 项目类别:面上项目
基于小世界网络的传感器网络研究
- 批准号:60472059
- 批准年份:2004
- 资助金额:21.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: III: Small: High-Performance Scheduling for Modern Database Systems
协作研究:III:小型:现代数据库系统的高性能调度
- 批准号:
2322973 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
Collaborative Research: III: Small: High-Performance Scheduling for Modern Database Systems
协作研究:III:小型:现代数据库系统的高性能调度
- 批准号:
2322974 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
Collaborative Research: III: Small: A DREAM Proactive Conversational System
合作研究:III:小型:一个梦想的主动对话系统
- 批准号:
2336769 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
Collaborative Research: III: Small: A DREAM Proactive Conversational System
合作研究:III:小型:一个梦想的主动对话系统
- 批准号:
2336768 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
III: Small: Multiple Device Collaborative Learning in Real Heterogeneous and Dynamic Environments
III:小:真实异构动态环境中的多设备协作学习
- 批准号:
2311990 - 财政年份:2023
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant