提出新方法实现图神经网络节点遗忘，无需重训且效果领先。
Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach
- 通过嵌入重建逆向聚合过程，实现节点级遗忘。
- 在多个数据集上达到当前最优性能，优于已有方法。
- 适合需要高效删除节点信息的图学习场景，如隐私保护。
图神经网络中的图遗忘旨在应对广泛而多样的图结构删除需求，但目前仍缺乏系统研究。现有图影响函数（GIF）仅在部分边删除时有效，难以处理更具挑战性的节点删除问题。为避免重新训练的开销并实现模型对遗忘操作的有效支持，本文提出一种新型节点遗忘方法：通过嵌入重建来逆向图神经网络中的聚合过程，并采用范围-零空间分解（Range-Null Space Decomposition）建模节点间交互。在多个代表性数据集上的实验表明，所提方法在多种删除场景下均表现优异，达到当前最优水平。
原文摘要 · Abstract (English)
Graph unlearning is tailored for GNNs to handle widespread and various graph structure unlearning requests, which remain largely unexplored. The GIF (graph influence function) achieves validity under partial edge unlearning, but faces challenges in dealing with more disturbing node unlearning. To avoid the overhead of retraining and realize the model utility of unlearning, we proposed a novel node unlearning method to reverse the process of aggregation in GNN by embedding reconstruction and to adopt Range-Null Space Decomposition for the nodes' interaction learning. Experimental results on multiple representative datasets demonstrate the SOTA performance of our proposed approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。