Collaborative Research: RI: Small: Robust Deep Learning with Big Imbalanced Data
合作研究:RI:小型:具有大不平衡数据的鲁棒深度学习
基本信息
- 批准号:2110545
- 负责人:
- 金额:$ 26.43万
- 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:2021-10-01 至 2022-11-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
This project promotes the progress of science and technology development by advancing artificial intelligence (AI) through innovations in scalable and robust computational methods. AI, especially deep learning, has brought transformative impact in industries and quantum leaps in the quality of a wide range of everyday technologies including face recognition, speech recognition and machine translation. However, in order to accelerate the democratization of AI there are still many challenges to be addressed including data issues and model issues. This project seeks to advance AI by addressing one critical issue related to data; i.e., data imbalance. This happens when the collected data for training AI models does not have enough instances representing some property the models are trying to learn. For example, molecules with a certain antibacterial property would be far fewer than all possible molecules making predictions of antibacterial properties challenging. The goal of this project is to develop algorithms with theoretical guarantees to make AI learn more effectively from the big imbalanced data. This project will also contribute to training future professionals in AI and machine learning, including training high school students and under-represented undergraduates. This project investigates a broad family of robust losses for deep learning. The research activities include (i) developing scalable offline stochastic algorithms for solving non-decomposable robust losses that are formulated into min-max, min-min formulations; (ii) developing efficient online stochastic algorithms for solving a family of distributionally robust optimization problems that are cast into compositional optimization problems; (iii) developing effective strategies for training deep neural networks by solving the considered non-decomposable robust losses; (iv) establishing the underlying theory including optimization and statistical convergence of the proposed algorithms. The algorithms are being evaluated on big imbalanced data such as images, graphs, texts.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.
该项目通过可扩展和强大的计算方法的创新来推进人工智能(AI),从而促进科学和技术发展的进步。人工智能,尤其是深度学习,为行业带来了变革性的影响,并为包括人脸识别、语音识别和机器翻译在内的各种日常技术带来了质的飞跃。然而,为了加速人工智能的民主化,仍然有许多挑战需要解决,包括数据问题和模型问题。该项目旨在通过解决与数据相关的一个关键问题来推进人工智能;即,数据不平衡当用于训练AI模型的收集数据没有足够的实例表示模型试图学习的某些属性时,就会发生这种情况。例如,具有某种抗菌特性的分子将远远少于所有可能的分子,使得抗菌特性的预测具有挑战性。该项目的目标是开发具有理论保证的算法,使人工智能更有效地从不平衡的大数据中学习。该项目还将有助于培训未来的人工智能和机器学习专业人员,包括培训高中生和代表性不足的本科生。 该项目研究了深度学习的一系列鲁棒损失。研究活动包括:(i)开发可扩展的离线随机算法,用于解决不可分解的鲁棒损失,这些损失被公式化为最小-最大,最小-最小公式;(ii)开发有效的在线随机算法,用于解决一族分布鲁棒优化问题,这些问题被转换为组合优化问题;(iii)通过解决所考虑的不可分解鲁棒损失来开发用于训练深度神经网络的有效策略;(iv)建立基础理论,包括所提出算法的优化和统计收敛。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值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(2)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives
- DOI:
- 发表时间:2020-06
- 期刊:
- 影响因子:0
- 作者:Qi Qi-Qi;Zhishuai Guo;Yi Xu;Rong Jin;Tianbao Yang
- 通讯作者:Qi Qi-Qi;Zhishuai Guo;Yi Xu;Rong Jin;Tianbao Yang
An Online Method for Distributionally Deep Robust Optimization
- DOI:
- 发表时间:2020-06
- 期刊:
- 影响因子:0
- 作者:Qi Qi-Qi;Zhishuai Guo;Yi Xu;Rong Jin;Tianbao Yang
- 通讯作者:Qi Qi-Qi;Zhishuai Guo;Yi Xu;Rong Jin;Tianbao Yang
{{
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 }}
Tianbao Yang其他文献
Evolution of the morphological, structural, and molecular properties of gluten protein in dough with different hydration levels during mixing.
- DOI:
10.1016/j.fochx.2022.100448 - 发表时间:
2022-10-30 - 期刊:
- 影响因子:6.1
- 作者:
Ruobing Jia;Mengli Zhang;Tianbao Yang;Meng Ma;Qingjie Sun;Man Li - 通讯作者:
Man Li
Improved bounds for the Nystrm method with application to kernel classification
改进 Nystr 的界限
- DOI:
- 发表时间:
2013 - 期刊:
- 影响因子:2.5
- 作者:
Rong Jin;Tianbao Yang;Mehrdad Mahdavi;Yu-Feng Li;Zhi-Hua Zhou - 通讯作者:
Zhi-Hua Zhou
Deep AUC Maximization for Medical Image Classification: Challenges and Opportunities
- DOI:
- 发表时间:
2021-11 - 期刊:
- 影响因子:0
- 作者:
Tianbao Yang - 通讯作者:
Tianbao Yang
Optimizing microgreen cultivation through post-crosslinked alginate-gellan gum hydrogel substrates with enhanced porosity and structural integrity
通过具有增强孔隙率和结构完整性的后交联海藻酸钠 - 结冷胶复合水凝胶基质优化微型蔬菜种植
- DOI:
10.1016/j.ijbiomac.2025.142905 - 发表时间:
2025-05-01 - 期刊:
- 影响因子:8.500
- 作者:
Ella Evensen;Zi Teng;Yimin Mao;Po-Yen Chen;Irma Ortiz;Yang Li;Tianbao Yang;Jorge M. Fonseca;Qin Wang;Yaguang Luo - 通讯作者:
Yaguang Luo
A Robust Zero-Sum Game Framework for Pool-based Active Learning
基于池的主动学习的鲁棒零和博弈框架
- DOI:
- 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
Dixian Zhu;Zhe Li;Xiaoyu Wang;Boqing Gong;Tianbao Yang - 通讯作者:
Tianbao Yang
Tianbao Yang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('Tianbao Yang', 18)}}的其他基金
Collaborative Research:SCH:Bimodal Interpretable Multi-Instance Medical-Image Classification
合作研究:SCH:双峰可解释多实例医学图像分类
- 批准号:
2306572 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
FAI: Advancing Optimization for Threshold-Agnostic Fair AI Systems
FAI:推进与阈值无关的公平人工智能系统的优化
- 批准号:
2147253 - 财政年份:2022
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Small: Robust Deep Learning with Big Imbalanced Data
合作研究:RI:小型:具有大不平衡数据的鲁棒深度学习
- 批准号:
2246756 - 财政年份:2022
- 资助金额:
$ 26.43万 - 项目类别:
Continuing Grant
CAREER: Advancing Constrained and Non-Convex Learning
职业:推进约束和非凸学习
- 批准号:
2246753 - 财政年份:2022
- 资助金额:
$ 26.43万 - 项目类别:
Continuing Grant
FAI: Advancing Optimization for Threshold-Agnostic Fair AI Systems
FAI:推进与阈值无关的公平人工智能系统的优化
- 批准号:
2246757 - 财政年份:2022
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
CAREER: Advancing Constrained and Non-Convex Learning
职业:推进约束和非凸学习
- 批准号:
1844403 - 财政年份:2019
- 资助金额:
$ 26.43万 - 项目类别:
Continuing Grant
Collaborative Research: Online Data Stream Fusion and Deep Learning for Virtual Meter in Smart Power Distribution Systems
合作研究:智能配电系统中虚拟电表的在线数据流融合和深度学习
- 批准号:
1933212 - 财政年份:2019
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
CRII: III: Scaling up Distance Metric Learning for Large-scale Ultrahigh-dimensional Data
CRII:III:扩大大规模超高维数据的距离度量学习
- 批准号:
1463988 - 财政年份:2015
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
BIGDATA: F: New Algorithms of Online Machine Learning for Big Data
BIGDATA:F:大数据在线机器学习的新算法
- 批准号:
1545995 - 财政年份:2015
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
相似国自然基金
Research on Quantum Field Theory without a Lagrangian Description
- 批准号:24ZR1403900
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
Cell Research
- 批准号:31224802
- 批准年份:2012
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research
- 批准号:31024804
- 批准年份:2010
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research (细胞研究)
- 批准号:30824808
- 批准年份:2008
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
- 批准号:10774081
- 批准年份:2007
- 资助金额:45.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: RI: Medium: Principles for Optimization, Generalization, and Transferability via Deep Neural Collapse
合作研究:RI:中:通过深度神经崩溃实现优化、泛化和可迁移性的原理
- 批准号:
2312841 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Medium: Principles for Optimization, Generalization, and Transferability via Deep Neural Collapse
合作研究:RI:中:通过深度神经崩溃实现优化、泛化和可迁移性的原理
- 批准号:
2312842 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Small: Foundations of Few-Round Active Learning
协作研究:RI:小型:少轮主动学习的基础
- 批准号:
2313131 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Medium: Lie group representation learning for vision
协作研究:RI:中:视觉的李群表示学习
- 批准号:
2313151 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Continuing Grant
Collaborative Research: RI: Small: Motion Fields Understanding for Enhanced Long-Range Imaging
合作研究:RI:小型:增强远程成像的运动场理解
- 批准号:
2232298 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Medium: Principles for Optimization, Generalization, and Transferability via Deep Neural Collapse
合作研究:RI:中:通过深度神经崩溃实现优化、泛化和可迁移性的原理
- 批准号:
2312840 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Small: Deep Constrained Learning for Power Systems
合作研究:RI:小型:电力系统的深度约束学习
- 批准号:
2345528 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: CompCog: RI: Medium: Understanding human planning through AI-assisted analysis of a massive chess dataset
合作研究:CompCog:RI:中:通过人工智能辅助分析海量国际象棋数据集了解人类规划
- 批准号:
2312374 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: CompCog: RI: Medium: Understanding human planning through AI-assisted analysis of a massive chess dataset
合作研究:CompCog:RI:中:通过人工智能辅助分析海量国际象棋数据集了解人类规划
- 批准号:
2312373 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant
Collaborative Research: RI: Small: End-to-end Learning of Fair and Explainable Schedules for Court Systems
合作研究:RI:小型:法院系统公平且可解释的时间表的端到端学习
- 批准号:
2232055 - 财政年份:2023
- 资助金额:
$ 26.43万 - 项目类别:
Standard Grant