As a way to implement the "right to be forgotten" in machine learning, \textit{machine unlearning} aims to completely remove the contributions and information of the samples to be deleted from a trained model without affecting the contributions of other samples. Recently, many frameworks for machine unlearning have been proposed, and most of them focus on image and text data. To extend machine unlearning to graph data, \textit{GraphEraser} has been proposed. However, a critical issue is that \textit{GraphEraser} is specifically designed for the transductive graph setting, where the graph is static and attributes and edges of test nodes are visible during training. It is unsuitable for the inductive setting, where the graph could be dynamic and the test graph information is invisible in advance. Such inductive capability is essential for production machine learning systems with evolving graphs like social media and transaction networks. To fill this gap, we propose the \underline{{\bf G}}\underline{{\bf U}}ided \underline{{\bf I}}n\underline{{\bf D}}uctiv\underline{{\bf E}} Graph Unlearning framework (GUIDE). GUIDE consists of three components: guided graph partitioning with fairness and balance, efficient subgraph repair, and similarity-based aggregation. Empirically, we evaluate our method on several inductive benchmarks and evolving transaction graphs. Generally speaking, GUIDE can be efficiently implemented on the inductive graph learning tasks for its low graph partition cost, no matter on computation or structure information. The code will be available here: https://github.com/Happy2Git/GUIDE.

翻译：作为机器学习中实现“被遗忘权”的一种方式，机器遗忘旨在在不影响其他样本贡献的前提下，从已训练模型中彻底移除待删除样本的贡献和信息。近期，已有多种机器遗忘框架被提出，其中大多数针对图像和文本数据。为将机器遗忘扩展到图数据，研究者提出了GraphEraser方法。然而，一个关键问题在于GraphEraser专门针对直推式图场景设计，该场景中图是静态的，且测试节点的属性与边在训练阶段可见。该方法不适用于归纳式场景，即图可能是动态的且测试图信息事先不可见。这种归纳能力对于社交网络、交易网络等具有动态演化图的生产级机器学习系统至关重要。为填补这一空白，我们提出GUIDE（Guided Inductive Graph Unlearning）框架。GUIDE包含三个组件：具有公平性和平衡性的引导式图划分、高效子图修复以及基于相似性的聚合。我们在多个归纳式基准数据集和动态交易图上对方法进行评估。总体而言，GUIDE凭借其低计算开销和结构信息依赖性低的图划分成本，可高效应用于归纳式图学习任务。代码开源地址：https://github.com/Happy2Git/GUIDE。