Forget Me, Not My Friends! Object Unlearning Based on Scene Graphs

Zhang, C; Zhao, B; Asghar, H; Wang, W; Liu, A; Kaafar, D

Forget Me, Not My Friends! Object Unlearning Based on Scene Graphs

Zhang, C

Zhao, B Asghar, H Wang, W Liu, A Kaafar, D

Permalink

Publisher:: Association for Computing Machinery (ACM)
Publication Type:: Conference Proceeding
Citation:: Wsdm 2026 Proceedings of the 19th ACM International Conference on Web Search and Data Mining, 2026, pp. 913-923
Issue Date:: 2026-02-21

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (4.96 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, C https://orcid.org/0000-0002-2352-0485
dc.contributor.author	Zhao, B
dc.contributor.author	Asghar, H
dc.contributor.author	Wang, W
dc.contributor.author	Liu, A
dc.contributor.author	Kaafar, D
dc.date.accessioned	2026-10-09T07:21:30Z
dc.date.available	2026-10-09T07:21:30Z
dc.date.issued	2026-02-21
dc.identifier.citation	Wsdm 2026 Proceedings of the 19th ACM International Conference on Web Search and Data Mining, 2026, pp. 913-923
dc.identifier.uri	http://hdl.handle.net/10453/197056
dc.description.abstract	Machine unlearning offers a practical technical means for fulfilling users' requests to remove personally identifiable information (PII) under ''right to be forgotten'' regulations such as GDPR and COPPA. Traditionally, unlearning is performed with the removal of entire data samples (sample unlearning) or whole features across the dataset (feature unlearning). However, when the removal request targets only certain parts of the PII, such as specific objects within a sample, these traditional unlearning approaches fall short of meeting such finer-grained unlearning requirements. To address this gap, we propose a scene graph-based object unlearning framework. This framework utilizes scene graphs, rich in semantic representation, transparently translate unlearning requests into actionable steps. The result, is the preservation of the overall semantic integrity of the generated image, bar the unlearned object. Furthermore, we develop three distinct approaches for object unlearning, grounded in the mainstream unlearning techniques of fine-tuning and model redaction. For validation, we evaluate the unlearned object's fidelity in outputs under the tasks of image reconstruction and image synthesis. Our proposed framework demonstrates improved object unlearning outcomes, with the preservation of unrequested samples in contrast to sample and feature learning methods. This work addresses critical privacy issues by increasing the granularity of targeted machine unlearning through forgetting specific object-level details without sacrificing the utility of the whole data sample or dataset feature.
dc.language	en
dc.publisher	Association for Computing Machinery (ACM)
dc.relation.ispartof	Wsdm 2026 Proceedings of the 19th ACM International Conference on Web Search and Data Mining
dc.relation.ispartof	Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining
dc.relation.isbasedon	10.1145/3773966.3777964
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Forget Me, Not My Friends! Object Unlearning Based on Scene Graphs
dc.type	Conference Proceeding
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2026-10-09T07:21:28Z
pubs.publication-status	Published

Abstract:

Machine unlearning offers a practical technical means for fulfilling users' requests to remove personally identifiable information (PII) under ''right to be forgotten'' regulations such as GDPR and COPPA. Traditionally, unlearning is performed with the removal of entire data samples (sample unlearning) or whole features across the dataset (feature unlearning). However, when the removal request targets only certain parts of the PII, such as specific objects within a sample, these traditional unlearning approaches fall short of meeting such finer-grained unlearning requirements. To address this gap, we propose a scene graph-based object unlearning framework. This framework utilizes scene graphs, rich in semantic representation, transparently translate unlearning requests into actionable steps. The result, is the preservation of the overall semantic integrity of the generated image, bar the unlearned object. Furthermore, we develop three distinct approaches for object unlearning, grounded in the mainstream unlearning techniques of fine-tuning and model redaction. For validation, we evaluate the unlearned object's fidelity in outputs under the tasks of image reconstruction and image synthesis. Our proposed framework demonstrates improved object unlearning outcomes, with the preservation of unrequested samples in contrast to sample and feature learning methods. This work addresses critical privacy issues by increasing the granularity of targeted machine unlearning through forgetting specific object-level details without sacrificing the utility of the whole data sample or dataset feature.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/197056