Orthogonal Soft Pruning for Efficient Class Unlearning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Qinghui, Yang, Xue, Tang, Xiaohu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917079829970944
author Gong, Qinghui
Yang, Xue
Tang, Xiaohu
author_facet Gong, Qinghui
Yang, Xue
Tang, Xiaohu
contents Efficient and controllable data unlearning in federated learning remains challenging, due to the trade-off between forgetting and retention performance. Especially under non-independent and identically distributed (non-IID) settings, where deep feature entanglement exacerbates this dilemma. To address this challenge, we propose FedOrtho, a federated unlearning framework that combines orthogonalized deep convolutional kernels with an activation-driven controllable one-shot soft pruning (OSP) mechanism. FedOrtho enforces kernel orthogonality and local-global alignment to decouple feature representations and mitigate client drift. This structural independence enables precise one-shot pruning of forgetting-related kernels while preserving retained knowledge. FedOrtho achieves SOTA performance on CIFAR-10, CIFAR100 and TinyImageNet with ResNet and VGG frameworks, verifying that FedOrtho supports class-, client-, and sample-level unlearning with over 98% forgetting quality. It reduces computational and communication costs by 2-3 orders of magnitude in federated settings and achieves subsecond-level erasure in centralized scenarios while maintaining over 97% retention accuracy and mitigating membership inference risks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Orthogonal Soft Pruning for Efficient Class Unlearning
Gong, Qinghui
Yang, Xue
Tang, Xiaohu
Machine Learning
Artificial Intelligence
Efficient and controllable data unlearning in federated learning remains challenging, due to the trade-off between forgetting and retention performance. Especially under non-independent and identically distributed (non-IID) settings, where deep feature entanglement exacerbates this dilemma. To address this challenge, we propose FedOrtho, a federated unlearning framework that combines orthogonalized deep convolutional kernels with an activation-driven controllable one-shot soft pruning (OSP) mechanism. FedOrtho enforces kernel orthogonality and local-global alignment to decouple feature representations and mitigate client drift. This structural independence enables precise one-shot pruning of forgetting-related kernels while preserving retained knowledge. FedOrtho achieves SOTA performance on CIFAR-10, CIFAR100 and TinyImageNet with ResNet and VGG frameworks, verifying that FedOrtho supports class-, client-, and sample-level unlearning with over 98% forgetting quality. It reduces computational and communication costs by 2-3 orders of magnitude in federated settings and achieves subsecond-level erasure in centralized scenarios while maintaining over 97% retention accuracy and mitigating membership inference risks.
title Orthogonal Soft Pruning for Efficient Class Unlearning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.19891