Inductive Graph Unlearning

Cheng Long Wang, Mengdi Huai, Di Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

As a way to implement the "right to be forgotten" in machine learning, machine unlearning aims to completely remove the contributions and information of the samples to be deleted from a trained model without affecting the contributions of other samples. Recently, many frameworks for machine unlearning have been proposed, and most of them focus on image and text data. To extend machine unlearning to graph data, GraphEraser has been proposed. However, a critical issue is that GraphEraser is specifically designed for the transductive graph setting, where the graph is static and attributes and edges of test nodes are visible during training. It is unsuitable for the inductive setting, where the graph could be dynamic and the test graph information is invisible in advance. Such inductive capability is essential for production machine learning systems with evolving graphs like social media and transaction networks. To fill this gap, we propose the GUided InDuctivE Graph Unlearning framework (GUIDE). GUIDE consists of three components: guided graph partitioning with fairness and balance, efficient subgraph repair, and similarity-based aggregation. Empirically, we evaluate our method on several inductive benchmarks and evolving transaction graphs. Generally speaking, GUIDE can be efficiently implemented on the inductive graph learning tasks for its low graph partition cost, no matter on computation or structure information. The code is available here: https://github.com/Happy2Git/GUIDE.

Original languageEnglish (US)
Title of host publication32nd USENIX Security Symposium, USENIX Security 2023
PublisherUSENIX Association
Pages3205-3222
Number of pages18
ISBN (Electronic)9781713879497
StatePublished - 2023
Event32nd USENIX Security Symposium, USENIX Security 2023 - Anaheim, United States
Duration: Aug 9 2023Aug 11 2023

Publication series

Name32nd USENIX Security Symposium, USENIX Security 2023
Volume5

Conference

Conference32nd USENIX Security Symposium, USENIX Security 2023
Country/TerritoryUnited States
CityAnaheim
Period08/9/2308/11/23

Bibliographical note

Publisher Copyright:
© USENIX Security 2023. All rights reserved.

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Inductive Graph Unlearning'. Together they form a unique fingerprint.

Cite this