CIF: Small: Efficient and Secure Federated Structure Learning from Bad Data

CIF：小型：高效、安全的联邦结构从不良数据中学习

• 批准号: 2341359
• 负责人: Namrata Vaswani
• 金额: $ 60万
• 依托单位: Iowa State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-06-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2341359&HistoricalAwards=false
• 关键词: CIF; Small; Efficient; Secure; Federated

This project develops secure distributed algorithms for efficiently solving a large class of optimization problems that occur in medical imaging and machine learning. Important examples include accelerated magnetic resonance imaging (MRI), product recommender systems, computer vision (e.g., occlusion removal or video editing), and bioinformatics (grouping of unlabeled data). The focus is on algorithms that are fast, require communicating only small amounts of data, and work well in the data-scarce regime. Algorithm speed is an important concern in all modern applications. Within MRI, it is essential for (near) real-time applications such as interventional MRI or on the fly identification and correction of artifacts, e.g., re-scanning if the patient coughs during the first scan. Sample efficiency is critical for accelerating the MRI scan, or for learning user ratings of products from very few available ones. The project also supports Early Math education via the CyMath program, a program in which Math-loving graduate students provide after-school Math tutoring support for students as young as third graders. This project introduces a novel solution framework called alternating gradient descent (GD) and minimization that provides a faster and more communication-efficient solution for many optimization problems for which alternating minimization (AltMin) is a popular solution. In particular, it is useful for any problem for which the minimization over one set of variables is much quicker than that over the other set. Starting with a careful initialization for one set, AltGDmin alternately updates the variables using minimization for the quicker set and gradient descent (GD) for the other set. Often, the reason that the minimization is fast over some variables is that the optimization problem is decoupled with respect to these variables. This decoupling also helps guarantee per-iteration communication-efficiency and privacy in federated settings. The use of minimization for one set of the variables is also what helps ensure sufficient error decay in each algorithm iteration. This implies that, for certain problems such as low rank column-wise sensing, AltGDmin is almost as fast and as communication-efficient per iteration as (factorized) GD, while converging almost as quickly as AltMin. This makes it faster overall than both types of solutions. Problem-specific correctness guarantees are derived. These determine the theoretical bounds on the iteration complexity and the sample complexity. Obtaining these results requires the development of novel proof techniques that may be of independent interest. The reason is AltGDmin is neither an AltMin approach nor a a standard GD algorithm for any subset of variables. The design and analysis Byzantine resilient (secure) AltGDmin algorithms is being studied for various low rank, and other structure, recovery problems.This project is jointly funded by the Computing and Communications Foundations (CCF) division of the Computer and Information Sciences Directorate (CISE) and the Established Program to Stimulate Competitive Research (EPSCoR).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.

该项目开发安全的分布式算法，用于有效解决医学成像和机器学习中出现的一大类优化问题。重要的例子包括加速磁共振成像（MRI）、产品推荐系统、计算机视觉（例如遮挡去除或视频编辑）和生物信息学（未标记数据的分组）。 重点是快速、仅需要传输少量数据并且在数据稀缺情况下运行良好的算法。 算法速度是所有现代应用中的一个重要问题。在 MRI 中，它对于（近）实时应用（例如介入 MRI 或动态识别和伪影校正（例如，如果患者在第一次扫描期间咳嗽则重新扫描））至关重要。 样本效率对于加速 MRI 扫描或从极少数可用产品中了解产品的用户评级至关重要。该项目还通过 CyMath 计划支持早期数学教育，在该计划中，热爱数学的研究生为三年级学生提供课后数学辅导支持。该项目引入了一种称为交替梯度下降 (GD) 和最小化的新颖解决方案框架，它为许多优化问题提供了更快、更高效的解决方案，其中交替最小化 (AltMin) 是一种流行的解决方案。特别是，它对于一组变量的最小化比另一组变量的最小化快得多的任何问题很有用。从一组的仔细初始化开始，AltGDmin 交替使用最小化更快的组和梯度下降 (GD) 更新另一组的变量。通常，某些变量的最小化速度很快的原因是优化问题与这些变量是解耦的。这种解耦还有助于保证联合设置中每次迭代的通信效率和隐私。对一组变量使用最小化也有助于确保每次算法迭代中足够的误差衰减。这意味着，对于某些问题（例如低秩列感知），AltGDmin 几乎与（因式分解）GD 一样快且每次迭代的通信效率相同，同时收敛速度几乎与 AltMin 一样快。这使得它总体上比这两种类型的解决方案更快。导出针对特定问题的正确性保证。这些决定了迭代复杂性和样本复杂性的理论界限。获得这些结果需要开发可能具有独立意义的新颖证明技术。原因是 AltGDmin 既不是 AltMin 方法，也不是任何变量子集的标准 GD 算法。 正在研究拜占庭弹性（安全）AltGDmin 算法的设计和分析，以解决各种低等级和其他结构、恢复问题。该项目由计算机和信息科学理事会 (CISE) 的计算和通信基金会 (CCF) 部门联合资助）和刺激竞争研究既定计划（EPSCoR）。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优点和更广泛的影响审查标准进行评估，被认为值得支持。