BIGDATA: F: Compositional Learning, Maps and Transfer: Statistical and Machine Learning on Collections of Data Sets

BIGDATA：F：组合学习、地图和迁移：数据集集合的统计和机器学习

• 批准号: 1837991
• 负责人: Mauro Maggioni
• 金额: $ 70万
• 依托单位: Johns Hopkins University
• 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: 2019-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1837991&HistoricalAwards=false
• 关键词: BIGDATA; Compositional; Learning; Maps; Transfer

One of the landmarks of human intelligence is the ability to not only find solutions to hard problems, but to learn from past experiences and accumulate knowledge that may be (partially) transferred for quickly solving new problems. This project will develop novel foundational techniques for learning compositional rules, from collections of data sets and machine learning problems. The building blocks that the investigator will develop enable sharing of learning across multiple data sets and modalities. A first building block will enable machine learning algorithms to store solutions to past problems and use maps and abstractions to transfer knowledge to new problems. This requires efficient techniques for learning maps, how to compose them to enable knowledge transfer, all in a way that is compatible with the representation of the problems and their solutions, which also need to be automatically learned. These ideas will be tested on problems ranging from object and pattern recognition of images to behavior of interacting agent systems, from fusing data sets acquired with different sensors to controlling virtual and real agents. This project will provide general, foundational results in machine learning, which can be applied to applications in virtually any domain of human endeavor. The investigator will develop new techniques focused on representation and transfer learning, in particular: (i) Compositional Learning: the ability to learn and factorize through composition maps between data sets, and of functions (for classification and regression tasks) on data sets (e.g. the task f may be learned by using the map h to one data set on which learning already occurred and the already-learned function g on that data), in order to enhance both learning rates, knowledge extraction and transfer across data sets and data types; (ii) Map Learning: the ability to efficiently learn, represent, store, recall and apply maps between complex data sets, possibly of different modalities; but also learn maps that transform, at least approximately, one task into another, and transfer knowledge from one task to another; (iii) Representation Learning: the ability to learn how to efficiently represent, store and recall complex data sets, across multiple sensor modalities, and across different levels of abstractions -- for example, learning efficient representations of data from multiple types of sensors, learning of classifiers and regression functions, or learning interaction kernels in agent-based systems, as well as transfer those functions across sensor modalities, data sets, dynamical systems. While advancing current state of art techniques in each of these learning abilities, the research will tackle applications in learning invariances and performing object recognition tasks in images, detecting whether objects in an image are new or known, learn interaction rules from observing trajectories of interacting agent systems, and implement the ideas of compositional learning in the context of learning systems both virtual (for examples, using the OpenAI challenges) and real (for example, using robots), on sequences of tasks of increasing difficulty.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.

人类智能的标志之一是不仅能够找到解决困难问题的方法，而且能够从过去的经验中学习并积累知识，这些知识可以（部分）转移用于快速解决新问题。该项目将开发新的基础技术，用于从数据集和机器学习问题的集合中学习组合规则。调查员将开发的构件能够在多个数据集和模式之间共享学习。第一个构建块将使机器学习算法能够存储过去问题的解决方案，并使用地图和抽象将知识转移到新问题。这就需要学习地图的有效技术，如何组合它们以实现知识转移，所有这些都需要与问题及其解决方案的表示兼容，这些问题及其解决方案也需要自动学习。这些想法将在从图像的对象和模式识别到交互代理系统的行为，从融合不同传感器获取的数据集到控制虚拟和真实的代理等问题上进行测试。 该项目将提供机器学习的一般性基础成果，这些成果可以应用于人类奋进的几乎任何领域的应用。研究人员将开发专注于表征和迁移学习的新技术，特别是：（i）组合学习：通过数据集之间的组合映射进行学习和分解的能力，和职能（用于分类和回归任务）（例如任务F可以通过使用到已经发生学习的一个数据集的映射H和关于该数据的已经学习的函数G来学习），为了提高学习率，知识提取和跨数据集和数据类型的转移;（ii）地图学习：有效学习，表示，存储，回忆和应用复杂数据集之间的地图的能力，可能是不同的模态;而且还学习至少近似地将一个任务转换为另一个任务的地图，并将知识从一个任务转移到另一个任务;（iii）表示学习：学习如何有效地表示、存储和调用复杂数据集、跨多个传感器模态和跨不同抽象级别的能力--例如，学习来自多种类型传感器的数据的有效表示、学习分类器和回归函数、或学习基于代理的系统中的交互内核，以及跨传感器模态、数据集动力系统 在推进这些学习能力中的每一种的当前最先进技术的同时，该研究将解决在学习不变性和执行图像中的对象识别任务中的应用，检测图像中的对象是新的还是已知的，通过观察交互代理系统的轨迹来学习交互规则，以及在学习系统的上下文中实现组合学习的想法。（例如，使用OpenAI挑战）和真实的（例如，使用机器人），在难度不断增加的任务序列上。该奖项反映了NSF的法定使命，并通过使用基金会的智力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

Learning by Active Nonlinear Diffusion

• DOI: 10.3934/fods.2019012
• 发表时间: 2019-05
• 期刊: ArXiv
• 作者: M. Maggioni;James M. Murphy

Learning Interaction Kernels in Stochastic Systems of Interacting Particles from Multiple Trajectories

学习多轨迹相互作用粒子随机系统中的相互作用核

• DOI: 10.1007/s10208-021-09521-z
• 发表时间: 2021
• 期刊: Foundations of Computational Mathematics
• 影响因子: 3
• 作者: Lu, Fei;Maggioni, Mauro;Tang, Sui
• 通讯作者: Tang, Sui

Learning Interaction Kernels for Agent Systems on Riemannian Manifolds

学习黎曼流形上代理系统的交互内核

• 发表时间: 2021
• 期刊: Proceedings of Machine Learning Research
• 作者: Mauro Maggioni, Jason J

Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms

• 发表时间: 2017-12
• 期刊: J. Mach. Learn. Res.
• 作者: A. Little;M. Maggioni;James M. Murphy

Conditional regression for single-index models

单指标模型的条件回归

• DOI: 10.3150/22-bej1482
• 发表时间: 2022
• 期刊: Bernoulli
• 影响因子: 1.5
• 作者: Lanteri, Alessandro;Maggioni, Mauro;Vigogna, Stefano
• 通讯作者: Vigogna, Stefano