Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning

TL;DR

The paper introduces Erase then Rectify (ETR), a training-free, scalable method for graph unlearning that effectively removes specific data influence from GNNs while maintaining model utility and reducing computational costs.

Contribution

This work presents a novel training-free approach for graph unlearning that combines parameter editing with gradient approximation to efficiently eliminate data influence without retraining.

Findings

ETR outperforms existing methods in unlearning efficiency.

ETR maintains high model utility after unlearning.

ETR demonstrates effectiveness across seven public datasets.

Abstract

Graph unlearning, which aims to eliminate the influence of specific nodes, edges, or attributes from a trained Graph Neural Network (GNN), is essential in applications where privacy, bias, or data obsolescence is a concern. However, existing graph unlearning techniques often necessitate additional training on the remaining data, leading to significant computational costs, particularly with large-scale graphs. To address these challenges, we propose a two-stage training-free approach, Erase then Rectify (ETR), designed for efficient and scalable graph unlearning while preserving the model utility. Specifically, we first build a theoretical foundation showing that masking parameters critical for unlearned samples enables effective unlearning. Building on this insight, the Erase stage strategically edits model parameters to eliminate the impact of unlearned samples and their propagated influence on intercorrelated nodes. To further ensure the GNN's utility, the Rectify stage devises a gradient approximation method to estimate the model's gradient on the remaining dataset, which is then used to enhance model performance. Overall, ETR achieves graph unlearning without additional training or full training data access, significantly reducing computational overhead and preserving data privacy. Extensive experiments on seven public datasets demonstrate the consistent superiority of ETR in model utility, unlearning efficiency, and unlearning effectiveness, establishing it as a promising solution for real-world graph unlearning challenges.