Collaborative Research: III: Small: Graph-Oriented Usable Interpretation

合作研究:III:小型:面向图形的可用解释

基本信息

  • 批准号:
    2223769
  • 负责人:
  • 金额:
    $ 28万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2022
  • 资助国家:
    美国
  • 起止时间:
    2022-10-01 至 2025-09-30
  • 项目状态:
    未结题

项目摘要

Interpretation holds great promise in gaining the trust of end-users by understanding how machine learning models work. In graph-based machine learning, although various interpretation methods have been proposed, the potential of interpretation has not been fully unleashed to make it a really useful tool. For example, existing interpretation methods can identify the important graph components (e.g., subgraph patterns and node features) given a model prediction, but they are not well equipped to shed light on other critical model properties, especially trustworthiness (e.g., fairness and robustness) that is crucial in many real-world applications. In addition, although the interpretation of graph models provides friendly visualization to humans for understanding, it remains nascent how the interpretation will inform the design of better models. To bridge the gap, this project takes a paradigm shift from traditional interpretation methods development, aiming to improve the usability of interpretation in graph learning system deployment, model training and data preparation. The results of this project will boost the overall value of interpretation in graph-based information systems. Furthermore, this research will play an integral part in educating and training undergraduate and PhD students. It will also be tightly integrated with multiple courses related to data mining and machine learning.This project aims to systematically explore usable interpretation in three different stages of a graph learning pipeline in backward order, ranging from system diagnosis, model improvement, back to data refinement. The project approaches interpretability through a novel perspective, which goes beyond conventional paradigms of simply understanding model predictions, towards explaining higher-level model properties and exploring how models could actually benefit from interpretation. First, it develops post-hoc interpretation tools to diagnose trustworthiness of graph learning models in various aspects, including fairness, robustness, and causality. Second, it develops interpretation-guided training algorithms and textual generative modules to comprehensively improve graph learning models in terms of effectiveness, robustness, and interactivity. Third, it utilizes interpretation to refine graph data from two complementary directions, including graph augmentation via a counterfactual Mixup strategy and graph compression via data distillation, which provide the fundamental basis of effective and efficient graph learning. The project will also result in the dissemination of shared data and open-source software to broader data mining and graph machine learning communities.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.
通过理解机器学习模型的工作原理,解释在获得最终用户的信任方面具有很大的希望。在基于图的机器学习中,虽然已经提出了各种解释方法,但解释的潜力尚未完全释放,使其成为真正有用的工具。例如,现有的解释方法可以识别重要的图组件(例如,子图模式和节点特征),但是它们不能很好地揭示其它关键模型属性,特别是可信度(例如,公平性和鲁棒性),这在许多实际应用中是至关重要的。此外,尽管图模型的解释为人类提供了友好的可视化理解,但解释如何为更好的模型设计提供信息仍然是新生的。为了弥合这一差距,本项目从传统的解释方法开发中进行了范式转换,旨在提高解释在图学习系统部署、模型训练和数据准备中的可用性。该项目的结果将提高基于图形的信息系统中解释的整体价值。此外,本研究将在教育和培养本科生和博士生中发挥不可或缺的作用。该项目旨在系统地探索图学习管道的三个不同阶段中的可用解释,从系统诊断,模型改进,到数据细化。该项目通过一种新的视角来研究可解释性,超越了简单理解模型预测的传统范式,而是解释更高层次的模型属性,并探索模型如何从解释中受益。首先,它开发了事后解释工具来诊断图学习模型在各个方面的可信度,包括公平性,鲁棒性和因果关系。其次,它开发了解释引导的训练算法和文本生成模块,以全面改善图学习模型的有效性,鲁棒性和交互性。第三,它利用解释从两个互补的方向细化图数据,包括通过反事实Mixup策略的图增强和通过数据蒸馏的图压缩,这为有效和高效的图学习提供了基础。该项目还将向更广泛的数据挖掘和图形机器学习社区传播共享数据和开源软件。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

期刊论文数量(19)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Federated Few-shot Learning
Fairness in Graph Mining: A Survey
  • DOI:
    10.1109/tkde.2023.3265598
  • 发表时间:
    2022-04
  • 期刊:
  • 影响因子:
    8.9
  • 作者:
    Yushun Dong;Jing Ma;Song Wang;Chen Chen-Chen;Jundong Li
  • 通讯作者:
    Yushun Dong;Jing Ma;Song Wang;Chen Chen-Chen;Jundong Li
Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
通过训练节点归因解释图神经网络中的不公平性
Few-shot Node Classification with Extremely Weak Supervision
Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification
  • DOI:
    10.48550/arxiv.2212.05606
  • 发表时间:
    2022-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Zhen Tan;Song Wang;Kaize Ding;Jundong Li;Huan Liu
  • 通讯作者:
    Zhen Tan;Song Wang;Kaize Ding;Jundong Li;Huan Liu
{{ 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 }}

Jundong Li其他文献

Online Collaborative Filtering with Implicit Feedback
具有隐式反馈的在线协同过滤
  • DOI:
    10.1007/978-3-030-18579-4_26
  • 发表时间:
    2019
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Jianwen Yin;Chenghao Liu;Jundong Li;Bingtian Dai;Yun;Min Wu;Jianling Sun
  • 通讯作者:
    Jianling Sun
Anlotinib combined with pemetrexed as a further treatment of patients with platinum-resistant ovarian cancer: A single-arm, open-label, phase II study
  • DOI:
    10.1016/s0090-8258(21)00758-7
  • 发表时间:
    2021-08-01
  • 期刊:
  • 影响因子:
  • 作者:
    Jueming Chen;Wei Wei;Lie Zheng;Han Li;Yanling Feng;Ting Wan;Jiaqi Qiu;Xingyu Jiang;Ying Xiong;Jundong Li;He Huang;Libing Song;Jihong Liu;Yanna Zhang
  • 通讯作者:
    Yanna Zhang
Synthesis of β-prolinols via [3+2] cycloaddition and one-pot programmed reduction: Valuable building blocks for polyheterocycles
通过[3 2]环加成和一锅程序还原合成β-脯氨醇:有价值的多杂环构建模块
  • DOI:
    10.1016/j.tetlet.2016.11.035
  • 发表时间:
    2016-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Jundong Li;Na Lin;Lei Yu;Y;ong Zhang
  • 通讯作者:
    ong Zhang
LookCom: Learning Optimal Network for Community Detection
LookCom:学习用于社区检测的最佳网络
PyGDebias: A Python Library for Debiasing in Graph Learning
PyGDebias:用于图学习中去偏的 Python 库
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yushun Dong;Zhenyu Lei;Zaiyi Zheng;Song Wang;Jing Ma;Alex Jing Huang;Chen Chen;Jundong Li
  • 通讯作者:
    Jundong Li

Jundong Li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('Jundong Li', 18)}}的其他基金

Travel: SDM 2024 Doctoral Forum Student Travel Grant
旅行:SDM 2024 博士论坛学生旅行补助金
  • 批准号:
    2400368
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
CAREER: Toward A Knowledge-Guided Framework for Personalized Decision Making
职业:走向个性化决策的知识引导框架
  • 批准号:
    2144209
  • 财政年份:
    2022
  • 资助金额:
    $ 28万
  • 项目类别:
    Continuing Grant
Collaborative Research: SAI-R: Dynamical Coupling of Physical and Social Infrastructures: Evaluating the Impacts of Social Capital on Access to Safe Well Water
合作研究:SAI-R:物理和社会基础设施的动态耦合:评估社会资本对获得安全井水的影响
  • 批准号:
    2228534
  • 财政年份:
    2022
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
III: Small: Collaborative Research: Demystifying Deep Learning on Graphs: From Basic Operations to Applications
III:小:协作研究:揭秘图深度学习:从基本操作到应用
  • 批准号:
    2006844
  • 财政年份:
    2020
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant

相似国自然基金

Research on Quantum Field Theory without a Lagrangian Description
  • 批准号:
    24ZR1403900
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
Cell Research
  • 批准号:
    31224802
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research
  • 批准号:
    31024804
  • 批准年份:
    2010
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research (细胞研究)
  • 批准号:
    30824808
  • 批准年份:
    2008
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
  • 批准号:
    10774081
  • 批准年份:
    2007
  • 资助金额:
    45.0 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: Conference: DESC: Type III: Eco Edge - Advancing Sustainable Machine Learning at the Edge
协作研究:会议:DESC:类型 III:生态边缘 - 推进边缘的可持续机器学习
  • 批准号:
    2342498
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Small: High-Performance Scheduling for Modern Database Systems
协作研究:III:小型:现代数据库系统的高性能调度
  • 批准号:
    2322973
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Small: High-Performance Scheduling for Modern Database Systems
协作研究:III:小型:现代数据库系统的高性能调度
  • 批准号:
    2322974
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: Conference: DESC: Type III: Eco Edge - Advancing Sustainable Machine Learning at the Edge
协作研究:会议:DESC:类型 III:生态边缘 - 推进边缘的可持续机器学习
  • 批准号:
    2342497
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
III : Medium: Collaborative Research: From Open Data to Open Data Curation
III:媒介:协作研究:从开放数据到开放数据管理
  • 批准号:
    2420691
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Small: A DREAM Proactive Conversational System
合作研究:III:小型:一个梦想的主动对话系统
  • 批准号:
    2336769
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Small: A DREAM Proactive Conversational System
合作研究:III:小型:一个梦想的主动对话系统
  • 批准号:
    2336768
  • 财政年份:
    2024
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Medium: Designing AI Systems with Steerable Long-Term Dynamics
合作研究:III:中:设计具有可操纵长期动态的人工智能系统
  • 批准号:
    2312865
  • 财政年份:
    2023
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: MEDIUM: Responsible Design and Validation of Algorithmic Rankers
合作研究:III:媒介:算法排序器的负责任设计和验证
  • 批准号:
    2312932
  • 财政年份:
    2023
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
Collaborative Research: III: Medium: Algorithms for scalable inference and phylodynamic analysis of tumor haplotypes using low-coverage single cell sequencing data
合作研究:III:中:使用低覆盖率单细胞测序数据对肿瘤单倍型进行可扩展推理和系统动力学分析的算法
  • 批准号:
    2415562
  • 财政年份:
    2023
  • 资助金额:
    $ 28万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了