Adaptive Graph Unlearning

2025-05-19

AI Summary

Graph forgetting in Graph Neural Networks (GNNs) aims to securely remove outdated, erroneous, or privacy-sensitive nodes/edges; however, existing methods suffer from incomplete forgetting, over-forgetting, or degraded generalization due to neglecting task heterogeneity and biased neighbor influence modeling. This paper proposes Adaptive Graph Unlearning (AGU), the first framework integrating gradient sensitivity analysis, architecture-aware neighbor propagation modeling, and importance-prioritized retraining. AGU dynamically adapts to diverse forgetting tasks and GNN architectures (e.g., GCN, GAT, GraphSAGE), precisely identifying and weighting critical neighbors affected by removed elements to enable selective and complete unlearning. Evaluated on seven real-world graph datasets, AGU improves forgetting accuracy by 12.6–28.3%, reduces inference overhead by 41%, and incurs less than 1.5% model accuracy degradation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Graph unlearning, which deletes graph elements such as nodes and edges from trained graph neural networks (GNNs), is crucial for real-world applications where graph data may contain outdated, inaccurate, or privacy-sensitive information. However, existing methods often suffer from (1) incomplete or over unlearning due to neglecting the distinct objectives of different unlearning tasks, and (2) inaccurate identification of neighbors affected by deleted elements across various GNN architectures. To address these limitations, we propose AGU, a novel Adaptive Graph Unlearning framework that flexibly adapts to diverse unlearning tasks and GNN architectures. AGU ensures the complete forgetting of deleted elements while preserving the integrity of the remaining graph. It also accurately identifies affected neighbors for each GNN architecture and prioritizes important ones to enhance unlearning performance. Extensive experiments on seven real-world graphs demonstrate that AGU outperforms existing methods in terms of effectiveness, efficiency, and unlearning capability.

Problem

• Deleting outdated or sensitive graph elements from GNNs
• Incomplete unlearning due to task-objective mismatch
• Inaccurate neighbor identification across GNN architectures

Innovation

• Adaptive framework for diverse unlearning tasks
• Accurate neighbor identification across GNN architectures
• Prioritizes important neighbors to enhance performance