Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach
Open accessAbstract
Data owners have the right to request for deleting their data from a machine learning (ML) model. In response, a naïve way is to retrain the model with the original dataset excluding the data to forget, which is however unrealistic as the required dataset may no longer be available and the retraining process is usually computationally expensive. To cope with this reality, machine unlearning has recently attained much attention, which aims to enable data removal from a trained ML model responding to deletion requests, without retraining the model from scratch or full access to the original training dataset. Existing unlearning methods mainly focus on handling conventional ML methods, while unlearning deep neural networks (DNNs) based models remains underexplored, especially for the ones trained on large-scale datasets.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Zhang et al.'s framework ensures that generated noisy data only affects the unlearning data being forgotten without affecting the contribution of other remaining data.
“They also proposed a new learning framework, which includes both static and dynamic learning branches, ensuring that the generated noisy data only affects the unlearning data being forgotten without affecting the contribution of other remaining data.”
From Machine Unlearning: A Survey (2024) · cites this paper as [63]
The above two schemes consume more time to generate noise for the unlearning process, which affects the efficiency of the unlearning process.
“However, the above two schemes consume more time to generate noise for unlearning process, which will affect the efficiency of the unlearning process [27, 63].”
From Machine Unlearning: A Survey (2024) · cites this paper as [63]
Zhang et al. [63] provided an unlearning scheme in image retrieval.
“For example, Zhang et al. [63] provided an unlearning scheme in image retrieval, while Chen et al. [47] considered graph unlearning problem.”
From Machine Unlearning: A Survey (2024) · cites this paper as [63]
The citation lists haven’t been fetched yet
References 34 · Cited by 18
- Authors
- Zhang, P.-F., Bai, G., Huang, Z., & Xu, X.-S.
- Affiliations
- The University of Queensland (AU)
- Shandong University (CN)
- Venue
- Proceedings of the 30th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2022-10-10
- Pages
- 237-245
- OpenAlex
- W4304091871
- Cited by
- 18
- References
- 34
- Citations by year
- 2026: 6 · 2025: 7 · 2024: 3 · 2023: 2
- FWCI
- 1.66
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion)
- Griffith Research Online (submittedVersion, other-oa)
- Funders
- Australian Research Council Discovery Project (DP190102353, CE200100025)
- China Scholarship Council
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- machine unlearning, image retrieval, deep neural network, privacy preservation, large-scale datasets
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
