2026-05-25原文

Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity

This paper introduces ManiF-SMC, a method for approximate machine unlearning that pushes erased samples away from their learned manifold centroids towards semantic neighbors in retained data, operating purely in representation space. A self-mode-connectivity module adaptively generates margins for triplet loss, achieving state-of-the-art unlearning effectiveness.

Article intelligence

EngineersAdvanced

Key points

ManiF-SMC approximates retraining behavior by moving erased samples toward semantic neighbors in representation space.
It employs a margin-based triplet loss with adaptive margins generated by a self-mode-connectivity module.
Experiments on four datasets show performance comparable to state-of-the-art approximate unlearning methods.

Why it matters

This matters because maniF-SMC approximates retraining behavior by moving erased samples toward semantic neighbors in representation space.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.22871] Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity

[Submitted on 20 May 2026]

Title:Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity

View a PDF of the paper titled Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity, by Weiqi Wang and 4 other authors

View PDF HTML (experimental)

Abstract:Machine unlearning is a fundamental mechanism that enforces the right to be forgotten. Existing unlearning studies that rely on label manipulation or task-gradient reversal often deliver limited unlearning effectiveness. Moreover, they can undermine the original learning objective and typically do not guarantee equivalence to standard unlearning by retraining.

In this paper, we propose \textbf{ManiF-SMC} (\textbf{Mani}fold \textbf{F}orgetting with \textbf{S}elf \textbf{M}ode \textbf{C}onnectivity), motivated by the observation that a model retrained on the remaining data tends to classify erased samples by their semantic similarity to the retained data. We begin with systematically recasting the approximate unlearning as pushing each erased sample away from its original learned manifold representation centroid toward its nearest semantic neighbors in the retained data. This reformulation aligns unlearning with retraining behavior and operates purely in representation space, reducing reliance on labels and task-specific gradients. To tackle the manifold representation-based unlearning problem, ManiF-SMC encapsulates the unlearning and representation preservation goals in a margin-based triplet loss. Because finding a suitable margin for unlearning is challenging, we propose a self-mode-connectivity module that rapidly reconstructs the local manifold to guide the adaptive margins generation for each unlearning case. Extensive experiments on four representative datasets show that ManiF-SMC achieves unlearning effectiveness comparable to state-of-the-art approximate methods while operating solely within the model's representation space.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)

Cite as: arXiv:2605.22871 [cs.LG]

(or arXiv:2605.22871v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.22871

arXiv-issued DOI via DataCite

Submission history

From: Weiqi Wang [view email] [v1] Wed, 20 May 2026 01:28:42 UTC (13,324 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity, by Weiqi Wang and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.AI stat stat.ML

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

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

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)