[论文解读] A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges

Wei Ju, Siyu Yi+11 more|arXiv (Cornell University)|Mar 7, 2024

Advanced Graph Neural Networks被引用 23

一句话总结

本文综述现实世界中图神经网络的挑战，聚焦不平衡、噪声、隐私和分布外（OOD）问题，并将现有方法整理为一个四类分类法并提出未来方向。

ABSTRACT

Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and network security. Significant strides have been made in leveraging Graph Neural Networks (GNNs) to achieve remarkable success in these areas. However, in real-world scenarios, the training environment for models is often far from ideal, leading to substantial performance degradation of GNN models due to various unfavorable factors, including imbalance in data distribution, the presence of noise in erroneous data, privacy protection of sensitive information, and generalization capability for out-of-distribution (OOD) scenarios. To tackle these issues, substantial efforts have been devoted to improving the performance of GNN models in practical real-world scenarios, as well as enhancing their reliability and robustness. In this paper, we present a comprehensive survey that systematically reviews existing GNN models, focusing on solutions to the four mentioned real-world challenges including imbalance, noise, privacy, and OOD in practical scenarios that many existing reviews have not considered. Specifically, we first highlight the four key challenges faced by existing GNNs, paving the way for our exploration of real-world GNN models. Subsequently, we provide detailed discussions on these four aspects, dissecting how these solutions contribute to enhancing the reliability and robustness of GNN models. Last but not least, we outline promising directions and offer future perspectives in the field.

研究动机与目标

• 在数据不完美且分布偏斜的现实世界条件下，促使研究GNNs。
• 提供一个系统化的方法分类法，解决不平衡、噪声、隐私和OOD这四大挑战。
• 总结各挑战的代表性算法与组件，并讨论实证洞见。
• 概述局限性并提出对鲁棒现实世界GNN模型的有前景方向。

提出的方法

• 提出一种新颖的分类法，将现实世界GNN模型分为不平衡、噪声、隐私和分布外（Out-of-Distribution）四类。
• 回顾用于解决不平衡的再平衡、基于增强的策略以及模块改进策略。
• 在噪声类别下讨论标签噪声和结构噪声，并综述相应的缓解技术。
• 概述隐私攻击与隐私保护方法，并区分隐私保护与攻击。
• 描述OOD检测与泛化方法以应对分布转移。

实验结果

研究问题

• RQ1 GNNs在现实世界中面临的主要挑战是什么（不平衡、噪声、隐私和OOD）？
• RQ2 研究人员在现实世界的GNN模型中如何对这四个挑战进行分类和应对？
• RQ3 每个挑战的代表性算法与组件是什么，它们的局限性与前景如何？
• RQ4 哪些未来方向可以引导更可靠、鲁棒的现实世界GNN的发展？

主要发现

• 指出GNNs在现实世界中的四个挑战：不平衡、噪声、隐私和OOD。
• 提出一个分类法并总结各类别的代表性方法，包括针对不平衡的再平衡、增强和模块改进策略。
• 概述两种噪声类型（标签噪声、结构噪声）及相应的缓解方法。
• 涵盖隐私攻击与隐私保护技术，以及OOD检测和OOD泛化类别。
• 强调当前调查的局限性，并强调2022年之后现实世界GNN研究中的最新进展。