🤖 AI Summary
Enforcing the “right to be forgotten” in graph machine learning poses unique challenges due to the structural dependency and propagation effects inherent in graph data, which fundamentally constrain feasibility and introduce novel theoretical obstacles absent in conventional forgetting learning.
Method: This work establishes the first unified taxonomy of Graph Forgetting Learning, integrating graph neural networks, differential privacy, incremental/decremental learning, model editing, and influence function analysis to develop the first evaluation framework for forgetting efficacy on graph-structured data.
Contribution: We provide a structured knowledge graph and a comprehensive survey covering applications in social networks, recommender systems, and IoT; deliver reproducible benchmarks and principled design patterns for privacy-compliant graph AI; and advance the practical implementation of the right to be forgotten in graph learning.
📝 Abstract
Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the right to be forgotten. It is evident that graph machine learning exhibits sensitivity to data privacy and adversarial attacks, necessitating the application of graph unlearning techniques to address these concerns effectively. In this comprehensive survey paper, we present the first systematic review of graph unlearning approaches, encompassing a diverse array of methodologies and offering a detailed taxonomy and up-to-date literature overview to facilitate the understanding of researchers new to this field. To ensure clarity, we provide lucid explanations of the fundamental concepts and evaluation measures used in graph unlearning, catering to a broader audience with varying levels of expertise. Delving into potential applications, we explore the versatility of graph unlearning across various domains, including but not limited to social networks, adversarial settings, recommender systems, and resource-constrained environments like the Internet of Things, illustrating its potential impact in safeguarding data privacy and enhancing AI systems' robustness. Finally, we shed light on promising research directions, encouraging further progress and innovation within the domain of graph unlearning. By laying a solid foundation and fostering continued progress, this survey seeks to inspire researchers to further advance the field of graph unlearning, thereby instilling confidence in the ethical growth of AI systems and reinforcing the responsible application of machine learning techniques in various domains.
