Interference-Aware Multi-Task Unlearning
Machine unlearning aims to remove designated training data from a model while preserving performance on remaining data. Existing work focuses on single-task settings, but modern models are often multi-task with shared backbones. This paper introduces multi-task unlearning with full-task and partial-task settings, and proposes an interference-aware framework combining task-aware gradient projection and instance-level gradient orthogonalization. Experiments on two multi-task computer vision benchmarks show a 30.3% reduction in UIS for full-task unlearning and 52.9% for partial-task unlearning compared to the strongest baseline.
[2605.19042] Interference-Aware Multi-Task Unlearning
[Submitted on 18 May 2026]
Title:Interference-Aware Multi-Task Unlearning
View a PDF of the paper titled Interference-Aware Multi-Task Unlearning, by Ying-Hua Huang and 3 other authors
View PDF HTML (experimental)
Abstract:Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work mainly focuses on single-task settings, whereas modern models often operate in multi-task setups with shared backbones, where removing supervision for one task or instance can unintentionally affect others. We introduce multi-task unlearning with two settings: full-task unlearning, which removes a target instance from all tasks, and partial-task unlearning, which removes supervision only from selected tasks. We show that shared parameters couple the forget and retain sets, causing task-level interference on non-target tasks and instance-level interference on other instances. To address this issue, we propose an interference-aware framework that combines task-aware gradient projection, which constrains updates within task-specific subspaces, with instance-level gradient orthogonalization, which reduces conflicts between forget and retain signals. Experiments on two multi-task computer vision benchmarks across five tasks show that our method achieves effective unlearning while maintaining strong generalization, reducing UIS compared with the strongest baseline by 30.3% in full-task unlearning and 52.9% in partial-task unlearning.
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.19042 [cs.AI]
(or arXiv:2605.19042v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.19042
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Rui Fang [view email] [v1] Mon, 18 May 2026 19:05:40 UTC (864 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Interference-Aware Multi-Task Unlearning, by Ying-Hua Huang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)