CAREER: A Novel Blueprint for Representation Learning of Relational Invariances

职业：关系不变性表示学习的新蓝图

• 批准号: 1943364
• 负责人: Bruno Ribeiro
• 金额: $ 49.12万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-05-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1943364&HistoricalAwards=false
• 关键词: CAREER; Novel; Blueprint; Representation; Learning

Graphs, tensors, and logical formulae are three of the most fundamental mathematical abstractions used to model complex data dependencies. These constructs are essential for the design of many modern AI innovations such as recommender systems in social networks, robots that reason about their environment, using generative models to design new drugs, or extracting business rules from data. Our theoretical understanding of graphs and tensors has significantly advanced in the past century, and the opportunity now exists for the development of practical tools for day-to-day machine-learning tasks. This research project aims to make available to neural network architectures data representations that are sufficiently expressive for complex tasks and computationally tractable for more tasks. This project leverages the PI’s prior work into a novel blueprint for better modeling complex relational input data, thereby translating the modern theoretical interpretation of sets, graphs, tensors, and logical formulae into provably more capable practical tools. The key insight is to leverage invariant theory to develop a novel framework for representation learning of complex relational data via approximate invariances. The full development of the framework of this proposal holds promise to harness the synergy between invariant theory and computational methods. Specifically, this study investigates: (a) most-expressive tractable models through ergodic theory and variational approximations; (b) adaptive model tractability and expressibility through invariance relaxations and quasi-invariant neural architectures; and (c) novel model evaluation metrics and tests of expressiveness for invariant representations. This project also explores the application of these methods on tasks defined on temporal graphs and tensors, sets and multisets, hypergraphs and simplices, logical formulae, and molecules. This project will also support substantial outreach activities, including workshop organization, course development, and the recruitment of underrepresented minorities to STEM careers.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.

图、张量和逻辑公式是用于为复杂数据依赖关系建模的三种最基本的数学抽象。这些结构对于许多现代人工智能创新的设计至关重要，比如社交网络中的推荐系统、对环境进行推理的机器人、使用生成模型设计新药，或者从数据中提取业务规则。在过去的一个世纪里，我们对图和张量的理论理解有了显著的进步，现在有机会开发用于日常机器学习任务的实用工具。本研究项目旨在为神经网络架构提供足够表达复杂任务的数据表示，并在计算上可处理更多任务。该项目利用PI之前的工作，为更好地建模复杂的关系输入数据构建了一个新的蓝图，从而将集、图、张量和逻辑公式的现代理论解释转化为可证明的更有能力的实用工具。关键的见解是利用不变量理论来开发一个新的框架，通过近似不变量来表示复杂关系数据的学习。该建议框架的充分发展有望利用不变量理论和计算方法之间的协同作用。具体而言，本研究通过遍历理论和变分近似研究了(a)最具表现力的可处理模型；(b)通过不变性松弛和准不变性神经结构实现自适应模型的可追溯性和可表达性；(c)新的模型评价指标和不变表示的可表达性检验。本项目还探讨了这些方法在时间图和张量、集和多集、超图和简单图、逻辑公式和分子上定义的任务中的应用。该项目还将支持大量的外展活动，包括研讨会组织、课程开发以及招募代表性不足的少数族裔从事STEM职业。该奖项反映了美国国家科学基金会的法定使命，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

Size-Invariant Graph Representations for Graph Classification Extrapolations

• 发表时间: 2021-03
• 期刊: ArXiv
• 作者: Beatrice Bevilacqua;Yangze Zhou;Bruno Ribeiro

An S-band Automatically Tunable Bandpass Filter Based on a Machine Learning Approach

基于机器学习方法的S波段自动可调谐带通滤波器

• 发表时间: 2021
• 期刊: 2021 IEEE 21st Annual Wireless and Microwave Technology Conference (WAMICON
• 作者: Adhikari, Pintu and

Causal lifting and link prediction

• DOI: 10.1098/rspa.2023.0121
• 发表时间: 2023-02
• 期刊: Proceedings of the Royal Society A
• 作者: Leonardo Cotta;Beatrice Bevilacqua;Nesreen Ahmed;Bruno Ribeiro

Deceptive Deletions for Protecting Withdrawn Posts on Social Media Platform

用于保护社交媒体平台上撤回帖子的欺骗性删除

• 发表时间: 2021
• 期刊: NDSS
• 作者: Minaei, Mohsen;Mouli, S Chandra;Mondal, Mainack;Ribeiro, Bruno;Kate, Aniket
• 通讯作者: Kate, Aniket

Neural Networks for Learning Counterfactual G-Invariances from Single Environments

用于从单一环境中学习反事实 G 不变性的神经网络

• 发表时间: 2021
• 期刊: Proceedings of the 9th International Conference on Learning Representations
• 作者: Mouli, S Chandra;Ribeiro, Bruno
• 通讯作者: Ribeiro, Bruno