FAI: Towards a Computational Foundation for Fair Network Learning

FAI:迈向公平网络学习的计算基础

基本信息

  • 批准号:
    1939725
  • 负责人:
  • 金额:
    $ 58.56万
  • 依托单位:
  • 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:
    2020-01-01 至 2024-12-31
  • 项目状态:
    已结题

项目摘要

Network learning and mining plays a pivotal role across a number of disciplines, such as computer science, physics, social science, management, neural science, civil engineering, and e-commerce. Decades of research in this area has provided a wealth of theories, algorithms and open-source systems to answer who/what types of questions. For example, who is the most influential in a social network? What items shall we recommend to a given user on an e-commerce platform? What Twitter poster is likely to go viral? Who can be grouped into the same online community? What financial transactions between users look suspicious? The state-of-the-art techniques on answering these questions have been widely adopted in various real-world applications, often with a strong empirical performance as well as a solid theoretic foundation. Despite the remarkable progress in network learning, a fundamental question largely remains nascent: how can we make network learning results and process explainable, transparent, and fair? The answer to this question benefits a variety of high-impact network learning based applications in terms of their interpretability, transparency and fairness, including social network analysis, neural science, team science and management, intelligent transportation systems, critical infrastructures, and blockchain networks.This project takes a shift for network learning, from answering who and what to answering how and why. It develops computational theories, algorithms and prototype systems in the context of network learning, forming three key pillars of fair network learning. The first pillar (interpretation) focuses on explaining the network learning results and process to end users, who are often not machine learning experts. In particular, this project develops theory and metrics to quantify the quality of explanations for network learning. Based on that, it brings explainability to network learning algorithms by carefully balancing the model fidelity and model interpretability. The second pillar (auditing) makes the network learning process transparent to end-users, focusing on demonstrating how the learning results of a given network learning algorithm relate to the underlying network structure. In particular, it develops a new fairness measure to accommodate the non-independent-and-identically-distributed nature of network learning. Based on this new fairness measure, it develops an algorithmic framework to audit a variety of network learning algorithms. The third pillar (de-biasing) explores how to mitigate potential biases to ensure fair network learning. Underpinning these pillars is a human-in-the-loop visual analytics framework to support users in identifying and mitigating bias in network learning. By assimilating the research outcome into the courses and summer programs that the research team has developed, this project trains students to value the spirit of fairness.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.
网络学习和挖掘在计算机科学、物理学、社会科学、管理学、神经科学、土木工程和电子商务等多个学科中发挥着关键作用。在这一领域数十年的研究提供了丰富的理论,算法和开源系统来回答谁/什么类型的问题。例如,谁在社交网络中最有影响力?在电子商务平台上,我们应该向特定用户推荐哪些商品?什么样的Twitter海报可能会像病毒一样传播?哪些人可以被归入同一个在线社区?用户之间的哪些金融交易看起来可疑?回答这些问题的最先进的技术已被广泛采用在各种现实世界的应用,往往具有强大的经验表现以及坚实的理论基础。尽管网络学习取得了显着的进步,但一个基本问题在很大程度上仍然存在:我们如何使网络学习的结果和过程可解释,透明和公平?这个问题的答案有利于各种高影响力的基于网络学习的应用程序在其可解释性,透明度和公平性方面,包括社交网络分析,神经科学,团队科学和管理,智能交通系统,关键基础设施和区块链网络。这个项目需要网络学习的转变,从回答谁和什么到回答如何和为什么。它在网络学习的背景下开发计算理论,算法和原型系统,形成公平网络学习的三个关键支柱。第一个支柱(解释)侧重于向最终用户解释网络学习的结果和过程,这些用户通常不是机器学习专家。特别是,该项目开发了理论和指标,以量化网络学习的解释质量。在此基础上,通过仔细平衡模型保真度和模型可解释性,为网络学习算法带来了可解释性。第二个支柱(审计)使网络学习过程对最终用户透明,重点是展示给定网络学习算法的学习结果如何与底层网络结构相关。特别是,它开发了一个新的公平性措施,以适应网络学习的非独立和同分布的性质。基于这种新的公平性度量,它开发了一个算法框架来审计各种网络学习算法。第三个支柱(去偏见)探讨如何减轻潜在的偏见,以确保公平的网络学习。支撑这些支柱的是一个人在回路的视觉分析框架,以支持用户识别和减轻网络学习中的偏见。通过将研究成果融入研究团队开发的课程和暑期项目,培养学生重视公平的精神。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

期刊论文数量(79)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Enhancing supervised bug localization with metadata and stack-trace
使用元数据和堆栈跟踪增强受监督的错误本地化
  • DOI:
    10.1007/s10115-019-01426-2
  • 发表时间:
    2020-02
  • 期刊:
  • 影响因子:
    2.7
  • 作者:
    Wang Yaojing;Yao Yuan;Tong Hanghang;Huo Xuan;Li Ming;Xu Feng;Lu Jian
  • 通讯作者:
    Lu Jian
Multiplex Graph Neural Network for Extractive Text Summarization
  • DOI:
    10.18653/v1/2021.emnlp-main.11
  • 发表时间:
    2021-08
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Baoyu Jing;Zeyu You;Tao Yang;Wei Fan;Hanghang Tong
  • 通讯作者:
    Baoyu Jing;Zeyu You;Tao Yang;Wei Fan;Hanghang Tong
Domain Adaptation in Physical Systems via Graph Kernel
Fast Connectivity Minimization on Large-Scale Networks
Sylvester Tensor Equation for Multi-Way Association
{{ 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 }}

Hanghang Tong其他文献

Multi-Aspect + Transitivity + Bias: An Integralnbsp;Trust Inference Modelbr /
多方面传递性偏差:积分
GTA3 2018: Workshop on Graph Techniques for Adversarial Activity Analytics
GTA3 2018:对抗性活动分析图技术研讨会
  • DOI:
  • 发表时间:
    2018
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Jiejun Xu;Hanghang Tong;Tsai;Jingrui He;Nadya Bliss
  • 通讯作者:
    Nadya Bliss
OnionGraph: Hierarchical topology+attribute multivariate network visualization
OnionGraph:层次拓扑属性多元网络可视化
  • DOI:
    10.1016/j.visinf.2020.01.002
  • 发表时间:
    2020-02
  • 期刊:
  • 影响因子:
    3
  • 作者:
    Lei Shi;Qi Liao;Hanghang Tong;Yifan Hu;Chaoli Wang;Chuang Lin;Weihong Qian
  • 通讯作者:
    Weihong Qian
Group Fairness via Group Consensus
通过群体共识实现群体公平
A unified optimization based learning method for image retrieval
一种基于统一优化的图像检索学习方法

Hanghang Tong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('Hanghang Tong', 18)}}的其他基金

Collaborative Research: III: Small: Reconstruction of Diffusion History in Cyber and Human Networks with Applications in Epidemiology and Cybersecurity
合作研究:III:小:重建网络和人类网络中的扩散历史及其在流行病学和网络安全中的应用
  • 批准号:
    2324770
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Standard Grant
Collaborative Research: Towards a Theoretic Foundation for Optimal Deep Graph Learning
协作研究:为最优深度图学习奠定理论基础
  • 批准号:
    2134079
  • 财政年份:
    2022
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Continuing Grant
CAREER: Network Robustification: Theories, Algorithms and Applications
职业:网络鲁棒化:理论、算法和应用
  • 批准号:
    1947135
  • 财政年份:
    2019
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Continuing Grant
EAGER: Collaborative Research: Correspondence Discovery in Disparate Networks
EAGER:协作研究:不同网络中的对应发现
  • 批准号:
    1743040
  • 财政年份:
    2017
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Standard Grant
CAREER: Network Robustification: Theories, Algorithms and Applications
职业:网络鲁棒化:理论、算法和应用
  • 批准号:
    1651203
  • 财政年份:
    2017
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Continuing Grant

相似海外基金

International Collaboration Towards Net Zero Computational Modelling and Simulation (CONTINENTS)
实现净零计算建模和仿真的国际合作(大陆)
  • 批准号:
    EP/Z531170/1
  • 财政年份:
    2024
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Research Grant
CAREER: Neural Computational Imaging - A Path Towards Seeing Through Scattering
职业:神经计算成像——透视散射的途径
  • 批准号:
    2339616
  • 财政年份:
    2024
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Continuing Grant
Towards machine ethics: Human and computational moral judgements of ethical decisions made by AI (Ref: 4659)
迈向机器伦理:人工智能做出的伦理决策的人类和计算道德判断(参考:4659)
  • 批准号:
    2859400
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Studentship
Computational fluid dynamics analysis using sophisticated plant models towards the development of digital twins in greenhouse horticulture
使用复杂的植物模型进行计算流体动力学分析,以开发温室园艺中的数字孪生
  • 批准号:
    23K05477
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
CRII: OAC: A Computational Framework for Studying Transport Phenomena in Complex Networks: From Biological Towards Sustainable and Resilient Engineering Networks
CRII:OAC:研究复杂网络中传输现象的计算框架:从生物网络到可持续和弹性工程网络
  • 批准号:
    2349122
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Standard Grant
Modeling the dynamics of belief formation: Towards a computational understanding of the timing and accuracy of probability judgments
对信念形成的动态进行建模:对概率判断的时间和准确性进行计算理解
  • 批准号:
    2350258
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Continuing Grant
Computational and Experimental Studies Towards Ideal Organic Semiconductors for Perovskite Solar Cells
用于钙钛矿太阳能电池的理想有机半导体的计算和实验研究
  • 批准号:
    2308895
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Standard Grant
Computational prediction of hot-electron chemistry: Towards electronic control of catalysis
热电子化学的计算预测:迈向催化的电子控制
  • 批准号:
    MR/X023109/1
  • 财政年份:
    2023
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Fellowship
Towards a computational model of distributed memory
走向分布式内存的计算模型
  • 批准号:
    546979-2020
  • 财政年份:
    2022
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Alexander Graham Bell Canada Graduate Scholarships - Doctoral
Computational biology of plant development: Towards a deductive science
植物发育的计算生物学:走向演绎科学
  • 批准号:
    RGPIN-2019-06279
  • 财政年份:
    2022
  • 资助金额:
    $ 58.56万
  • 项目类别:
    Discovery Grants Program - Individual
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了