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

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。

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.