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
基本信息
- 批准号:2313130
- 负责人:
- 金额:$ 30万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-08-01 至 2026-07-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Supervised machine learning has found widespread application, often achieving state-of-the-art performance. However, these algorithms rely on labeled training instances, which can be challenging to acquire. Labeled instances are often done by humans and require time and money to obtain. Active Learning strives to minimize labeling costs by identifying the most informative instances for annotation. While Active Learning techniques have shown promise in producing high-performance models with fewer labels, their applications remain constrained due to the necessity for multiple interaction rounds with annotators, which can be time-consuming or infeasible. This project aims to advance Active Learning algorithms and understanding of their fundamental capabilities in scenarios with limited interaction rounds. A broad spectrum of machine learning applications is expected to benefit from the results of this research, reducing the time and cost associated with obtaining sufficient data for training accurate models. Additionally, this project engages underrepresented minority students through hands-on research and learning activities, develops course modules on resource-efficient machine learning, and disseminates our findings to industry and academia via an extensive online Active Learning tutorial.This project will launch a comprehensive investigation of few-round active learning, where the learner can actively request feedback on specific data points within a limited number of rounds. To achieve this, the project will interleave two algorithmic tasks: robust data utility quantification and planning with limited adaptivity. First, the investigators will explore methods to measure the utility of unlabeled data, taking into account data size, underlying data characteristics, and downstream learning tasks. Subsequently, the team will develop algorithms that optimize the data utility metric while simultaneously improving the metric's quality over time in a few-round active learning setting. The project findings will establish principled approaches for addressing a novel exploration-exploitation dilemma specific to few-round active learning and provide a fundamental understanding of adaptivity's role in budgeted learning. Finally, the project will evaluate the proposed approaches across various high-impact machine learning applications, including autonomous driving, smart buildings, dialog systems, and biochemical engineering.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.
监督机器学习已经得到了广泛的应用,通常可以实现最先进的性能。然而,这些算法依赖于标记的训练实例,这可能具有挑战性。标记实例通常由人类完成,需要时间和金钱才能获得。 主动学习通过识别最具信息性的注释实例来尽量减少标记成本。虽然主动学习技术在产生具有较少标签的高性能模型方面表现出了希望,但由于需要与注释器进行多轮交互,因此其应用仍然受到限制,这可能是耗时或不可行的。该项目旨在推进主动学习算法,并在有限交互回合的情况下了解其基本功能。预计广泛的机器学习应用将受益于这项研究的结果,减少与获得足够数据以训练准确模型相关的时间和成本。此外,该项目通过实践研究和学习活动吸引少数民族学生,开发资源高效机器学习的课程模块,并通过广泛的在线主动学习教程向行业和学术界传播我们的研究结果。该项目将对几轮主动学习进行全面调查,其中学习者可以在有限数量的轮内主动请求关于特定数据点的反馈。为了实现这一目标,该项目将交错两个算法任务:强大的数据效用量化和有限适应性规划。首先,研究人员将探索衡量未标记数据效用的方法,同时考虑数据大小、基础数据特征和下游学习任务。随后,该团队将开发优化数据效用度量的算法,同时在几轮主动学习环境中随着时间的推移提高度量的质量。该项目的研究结果将建立一个新的探索开发的困境,具体到几轮主动学习的原则性方法,并提供了一个基本的理解适应性的预算学习的作用。最后,该项目将评估各种高影响力机器学习应用的拟议方法,包括自动驾驶,智能建筑,对话系统和生化工程。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(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Ruoxi Jia其他文献
Data Shapley in One Training Run
一次训练中的数据 Shapley
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Jiachen T. Wang;Prateek Mittal;Dawn Song;Ruoxi Jia - 通讯作者:
Ruoxi Jia
Efficient Data Shapley for Weighted Nearest Neighbor Algorithms
用于加权最近邻算法的高效数据 Shapley
- DOI:
10.48550/arxiv.2401.11103 - 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Jiachen T. Wang;Prateek Mittal;Ruoxi Jia - 通讯作者:
Ruoxi Jia
One-Round Active Learning through Data Utility Learning and Proxy Models
通过数据效用学习和代理模型进行一轮主动学习
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
Jiachen T. Wang;Si Chen;Ruoxi Jia;Virginia Tech;T. Jiachen;Wang - 通讯作者:
Wang
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
BEEAR:基于嵌入的对抗性删除指令调整语言模型中的安全后门
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Yi Zeng;Weiyu Sun;Tran Ngoc Huynh;Dawn Song;Bo Li;Ruoxi Jia - 通讯作者:
Ruoxi Jia
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
人工智能风险分类解读(AIR 2024):从政府法规到企业政策
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Yi Zeng;Kevin Klyman;Andy Zhou;Yu Yang;Minzhou Pan;Ruoxi Jia;Dawn Song;Percy Liang;Bo Li - 通讯作者:
Bo Li
Ruoxi Jia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('Ruoxi Jia', 18)}}的其他基金
CAREER: Data Valuation in the Wild: Theories, Algorithms, and Applications
职业:野外数据评估:理论、算法和应用
- 批准号:
2239622 - 财政年份:2023
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
III: Medium: Towards Inclusive Recommendation Systems with Stakeholder Alignment
III:中:迈向利益相关者联盟的包容性推荐系统
- 批准号:
2312794 - 财政年份:2023
- 资助金额:
$ 30万 - 项目类别:
Continuing 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:
$ 30万 - 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:
$ 30万 - 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:
$ 30万 - 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:
$ 30万 - 项目类别:
Continuing 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:
$ 30万 - 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:
$ 30万 - 项目类别:
Standard 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:
$ 30万 - 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:
$ 30万 - 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:
2313149 - 财政年份:2023
- 资助金额:
$ 30万 - 项目类别:
Continuing 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:
$ 30万 - 项目类别:
Standard Grant