Unlearning Graph Classifiers with Limited Data Resources

Chao Pan, Eli Chien, Olgica Milenkovic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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% increase in test accuracy during unlearning of 90 out of 100 training graphs from the IMDB dataset (10% training ratio). Our implementation is available online at https://doi.org/10.5281/zenodo.7613150.

Original languageEnglish (US)
Title of host publicationACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023
PublisherAssociation for Computing Machinery
Pages716-726
Number of pages11
ISBN (Electronic)9781450394161
DOIs
StatePublished - Apr 30 2023
Event2023 World Wide Web Conference, WWW 2023 - Austin, United States
Duration: Apr 30 2023May 4 2023

Publication series

NameACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023

Conference

Conference2023 World Wide Web Conference, WWW 2023
Country/TerritoryUnited States
CityAustin
Period4/30/235/4/23

Keywords

  • Graph neural networks
  • graph scattering transforms
  • graph unlearning
  • machine unlearning
  • small data sample regime

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Fingerprint

Dive into the research topics of 'Unlearning Graph Classifiers with Limited Data Resources'. Together they form a unique fingerprint.

Cite this