AF:Small:Unifying Information Aggregation and Information Elicitation

AF:Small：统一信息聚合和信息获取

• 批准号: 2007256
• 负责人: Grant Schoenebeck
• 金额: $ 34.99万
• 依托单位: Regents of the University of Michigan - Ann Arbor
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2007256&HistoricalAwards=false
• 关键词: AF; Small; Unifying; Information; Aggregation

Crowdsourcing is an approach to solving problems via distributed effort. In the future, crowdsourcing mechanisms should prove useful in gathering and aggregating information in a variety of contexts including basic scientific research, reputation systems, peer grading, and many decision-making contexts including purchasing, product development, pricing, etc. This project will design practical crowdsourcing mechanisms to incentivize users to report accurate data, even when the veracity cannot be directly verified. A key part of this is accurately measuring the quality of the information reported. Building mechanisms sufficiently robust for dealing with diverse types of agents is necessary for the success of this proposal. Thus, it has applications beyond crowdsourcing to big data more broadly (interpreting data from diverse sources of varying reliability) and algorithmic fairness. The research efforts will be integrated with the educational and outreach activities of the investigator, who has a record of broadly disseminating cutting-edge research to high school, undergraduate, and graduate students through teaching, outreach programs, and personal mentoring.Recent developments in the field of information elicitation show how to use information-theoretic concepts to truthfully elicit unverifiable information from agents. The heart of these results is first to employ clever techniques to indirectly measure ``mutual information" between agents, then to compensate agents proportionally to the mutual information measurement. There is also increasing work in learning theory, especially to enable learning with noisy or adversarial data. The goal of this proposal is to create a bridge between the information-elicitation and information-aggregation tasks. By using an information-theoretic underpinning we can unify the progress of these fields, and, in many instances, fuse these tasks together. The project will undertake the following. 1) Design full pipeline systems by uniting the techniques of information elicitation and aggregation into one streamlined process. 2) Examine how to better measure information-theoretic concepts required for truthful elicitation algorithms. 3) Address important concerns such as algorithmic fairness, optimal and realistic payments, and robustness. Moreover, this proposal will help to better integrate information theory into the computer-science community, which is essential in the era of data science.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.

众包是一种通过分布式努力解决问题的方法。 在未来，众包机制应证明有用的收集和汇总信息的各种情况下，包括基础科研，信誉系统，同行评级，和许多决策的情况下，包括采购，产品开发，定价等，该项目将设计实用的众包机制，以激励用户报告准确的数据，即使在真实性不能直接验证。 其中一个关键部分是准确衡量所报告信息的质量。 建立足够强大的机制来处理不同类型的代理人是这项建议成功的必要条件。 因此，它的应用范围超出了众包，更广泛地应用于大数据（解释来自不同可靠性来源的数据）和算法公平性。 研究工作将与研究者的教育和推广活动相结合，研究者通过教学、推广计划和个人指导向高中生、本科生和研究生广泛传播前沿研究成果。信息获取领域的最新发展表明，如何使用信息理论概念从代理人那里真实地获取无法验证的信息。 这些结果的核心是首先采用巧妙的技术来间接测量代理之间的“互信息”，然后按比例补偿代理的互信息测量。 在学习理论方面也有越来越多的工作，特别是在使用噪声或对抗性数据进行学习方面。 该提案的目标是在信息获取和信息汇总任务之间建立一座桥梁。 通过使用信息理论的基础，我们可以统一这些领域的进展，并且在许多情况下，将这些任务融合在一起。该项目将开展以下工作。1)通过将信息获取和聚合技术结合到一个流线型流程中来设计完整的管道系统。 2)研究如何更好地测量真实启发算法所需的信息理论概念。 3)解决算法公平性、最佳和现实支付以及鲁棒性等重要问题。 此外，这一提议将有助于更好地将信息理论融入计算机科学界，这在数据科学时代至关重要。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

SURPRISE! and When to Schedule It.

惊喜！

• DOI: 10.24963/ijcai.2021/36
• 发表时间: 2021
• 期刊: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
• 作者: Huang, Zhihuan;Xu, Shengwei;Shan, You;Lu, Yuxuan;Kong, Yuqing;Liu, Tracy Xiao;Schoenebeck, Grant
• 通讯作者: Schoenebeck, Grant

Bayesian Persuasion in Sequential Trials

• DOI: 10.1007/978-3-030-94676-0_2
• 发表时间: 2021-10
• 期刊: ArXiv
• 作者: Shih-Tang Su;V. Subramanian;G. Schoenebeck

Optimal Local Bayesian Differential Privacy over Markov Chains

马尔可夫链上的最优局部贝叶斯差分隐私

• 发表时间: 2022
• 期刊: AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems
• 作者: Chakrabarti, Darshan and

Timely Information from Prediction Markets

来自预测市场的及时信息

• 发表时间: 2021
• 期刊: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems
• 作者: Schoenebeck, Grant;Yu, Chenkai;Yu, Fang-Yi
• 通讯作者: Yu, Fang-Yi

Wisdom of the Crowd Voting: Truthful Aggregation of Voter Information and Preferences

群体投票的智慧：选民信息和偏好的真实汇总

• 发表时间: 2021
• 期刊: Advances in neural information processing systems
• 作者: Schoenebeck, Grant and