Unlearning Nonlinear Graph Classifiers in the Limited Training Data Regime

by   Chao Pan, et al.

As the demand for user privacy grows, controlled data removal (machine unlearning) is becoming an important feature of machine learning models for data-sensitive Web applications such as social networks and recommender systems. Nevertheless, at this point it is still largely unknown how to perform efficient machine unlearning of graph neural networks (GNNs); this is especially the case when the number of training samples is small, in which case unlearning can seriously compromise the performance of the model. To address this issue, we initiate the study of unlearning the Graph Scattering Transform (GST), a mathematical framework that is efficient, provably stable under feature or graph topology perturbations, and offers graph classification performance comparable to that of GNNs. Our main contribution is the first known nonlinear approximate graph unlearning method based on GSTs. Our second contribution is a theoretical analysis of the computational complexity of the proposed unlearning mechanism, which is hard to replicate for deep neural networks. Our third contribution are extensive simulation results which show that, compared to complete retraining of GNNs after each removal request, the new GST-based approach offers, on average, a 10.38x speed-up and leads to a 2.6 training graphs from the IMDB dataset (10


page 1

page 2

page 3

page 4


FairGNN: Eliminating the Discrimination in Graph Neural Networks with Limited Sensitive Attribute Information

Graph neural networks (GNNs) have shown great power in modeling graph st...

Toward the Analysis of Graph Neural Networks

Graph Neural Networks (GNNs) have recently emerged as a robust framework...

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

Graph neural networks (GNNs) which apply the deep neural networks to gra...

Certified Graph Unlearning

Graph-structured data is ubiquitous in practice and often processed usin...

Scalable Graph Neural Network Training: The Case for Sampling

Graph Neural Networks (GNNs) are a new and increasingly popular family o...

Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments

Graph representation learning is gaining popularity in a wide range of a...

Please sign up or login with your details

Forgot password? Click here to reset