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

合作研究：III：小型：面向图形的可用解释

• 批准号: 2223769
• 负责人: Jundong Li
• 金额: $ 28万
• 依托单位: University of Virginia Main Campus
• 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
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2223769&HistoricalAwards=false
• 关键词: Collaborative; Research; III; Small; Graph

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，口译在赢得最终用户信任方面大有可为。在基于图的机器学习中，虽然已经提出了各种解释方法，但解释的潜力还没有完全释放出来，使其成为一个真正有用的工具。例如，现有的解释方法可以在给定模型预测的情况下识别重要的图组件(例如，子图模式和节点特征)，但是它们不能很好地阐明其他关键的模型属性，特别是在许多真实世界应用中至关重要的可信性(例如，公平性和稳健性)。此外，尽管图形模型的解释为人类的理解提供了友好的可视化，但解释将如何为更好的模型的设计提供信息仍处于萌芽状态。为了弥合这一差距，该项目从传统的解释方法开发进行了范式转变，旨在提高解释在图形学习系统部署、模型训练和数据准备中的可用性。该项目的成果将提高基于图表的信息系统中口译的整体价值。此外，本研究将对本科生和博士生的教育和培养起到不可或缺的作用。它还将与与数据挖掘和机器学习相关的多门课程紧密结合。该项目旨在按倒序在图形学习管道的三个不同阶段系统地探索可用的解释，范围从系统诊断、模型改进到数据改进。该项目通过一种新的视角来探讨可解释性，这种视角超越了简单理解模型预测的传统范式，而是解释更高级别的模型属性，并探索模型如何从解释中实际受益。首先，它开发了后自组织解释工具来诊断图学习模型的可信性，包括公平性、稳健性和因果关系。其次，开发了口译指导的训练算法和文本生成模块，在有效性、稳健性和互动性方面全面改进了图形学习模型。第三，它利用解释从两个互补的方向提炼图形数据，包括通过反事实混合策略的图形增强和通过数据提取的图形压缩，这为有效和高效的图形学习提供了基本的基础。该项目还将导致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智力优势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

Federated Few-shot Learning

• DOI: 10.1145/3580305.3599347
• 发表时间: 2023-06
• 期刊: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Song Wang;Xingbo Fu;Kaize Ding;Chen Chen-Chen;Huiyuan Chen;Jundong Li

Fairness in Graph Mining: A Survey

• DOI: 10.1109/tkde.2023.3265598
• 发表时间: 2022-04
• 期刊: IEEE Transactions on Knowledge and Data Engineering
• 影响因子: 8.9
• 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

• DOI: 10.1609/aaai.v37i6.25905
• 发表时间: 2023
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Dong, Yushun;Wang, Song;Ma, Jing;Liu, Ninghao;Li, Jundong
• 通讯作者: Li, Jundong

Few-shot Node Classification with Extremely Weak Supervision

• DOI: 10.1145/3539597.3570435
• 发表时间: 2023-01
• 期刊: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining
• 作者: Song Wang;Yushun Dong;Kaize Ding;Chen Chen-Chen;Jundong Li

Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

• DOI: 10.48550/arxiv.2212.05606
• 发表时间: 2022-12
• 作者: Zhen Tan;Song Wang;Kaize Ding;Jundong Li;Huan Liu