Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA

• URL: http://arxiv.org/abs/2604.12526v1
• Date: Tue, 14 Apr 2026 09:59:32 GMT
• Title: Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA
• Abstract summary: Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else.<n>Low-Rank Adaptation (LoRA) offers an efficient way to implement such updates, but naively combining many sequential LoRA modules leads to parameter collision.<n>We propose a static alternative based on Singular Value Decomposition (SVD)-guided orthogonal subspace projection.
• Score: 8.191149161025198
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting becomes especially difficult when deletion requests arrive sequentially, because the model must repeatedly adapt without erasing previously retained knowledge. Low-Rank Adaptation (LoRA) offers an efficient way to implement such updates, but naively combining many sequential LoRA modules leads to parameter collision, causing \textit{strong interference} between tasks. We propose a static alternative based on Singular Value Decomposition (SVD)-guided orthogonal subspace projection. Our method constrains each new LoRA update during training so that it lies in the orthogonal complement of the subspaces used by earlier unlearning tasks. This preserves task isolation without requiring dynamic routing at deployment. Experiments on CIFAR-100 with ResNet-20 and on MNIST show stable behavior across long sequences of unlearning tasks. After thirty sequential unlearning tasks, state-of-the-art static fusion reduces retained accuracy from 60.39\% to 12.70\%, whereas the proposed in-training constrained optimization maintains baseline performance ($\sim$58.1\%) while preserving strong unlearning efficacy.

Related papers

• Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning [2.749219725903528]
  Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially.<n>LoRA-based continual learning methods allocate a separate low-rank adapter per task, yet existing approaches either require task identity at inference or sum all adapters indiscriminately.<n>Recent gating-based solutions route inputs to the correct adapter but introduce trainable parameters that themselves need protection against forgetting.<n>Latent-LoRA is replay-free, requires no trainable routing component, and uses substantially fewer parameters per task.
  arXiv  Detail & Related papers  (2026-07-26T20:42:56Z)
• Label-Free Cross-Task LoRA Merging with Null-Space Compression [50.63908869296697]
  We introduce Null-Space Compression (NSC) Merging, a label-free, output-agnostic method that sets merge weights from adapter geometry.<n>NSC achieves state-of-the-art performance across twenty heterogeneous vision tasks with balanced gains where prior methods overfit subsets of tasks.
  arXiv  Detail & Related papers  (2026-03-27T11:34:41Z)
• Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA [50.97792275353563]
  We introduce a novel framework that restructures a single Low-Rank Adaptation (LoRA) module as a decomposable Rank-1 Expert Pool.<n>Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the [Guided] token.
  arXiv  Detail & Related papers  (2026-01-30T10:54:51Z)
• LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning [9.009523608709117]
  On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments.<n>Existing activation compression methods reduce this cost but rely on repeated low-rank decompositions, introducing computational overhead.<n>We propose LANCE, a framework that performs one-shot higher-order Singular Value Decompsoition (SVD) to obtain a reusable low-rank subspace for activation projection.
  arXiv  Detail & Related papers  (2025-09-25T21:33:40Z)
• Continuous Subspace Optimization for Continual Learning [24.597922531045846]
  Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge.<n>We propose Continuous Subspace Optimization for Continual Learning (CoSO) to fine-tune the model in a series of subspaces rather than a single one.<n>CoSO significantly outperforms state-of-the-art methods, especially in challenging scenarios with long task sequences.
  arXiv  Detail & Related papers  (2025-05-17T03:53:21Z)
• LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning [5.438329886561997]
  We introduce the Drift-Resistant Space (DRS), which effectively handles feature drifts without requiring explicit feature modeling or the storage of previous tasks.<n>Our method consistently achieves state-of-the-art results, especially for long task sequences, across multiple datasets.
  arXiv  Detail & Related papers  (2025-03-23T07:38:53Z)
• Adaptive Retention & Correction: Test-Time Training for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task.<n>We name our approach Adaptive Retention & Correction (ARC)<n>ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning [60.501201259732625]
  We introduce task-adaptive saliency for EFCIL and propose a new framework, which we call Task-Adaptive Saliency Supervision (TASS) Our experiments demonstrate that our method can better preserve saliency maps across tasks and achieve state-of-the-art results on the CIFAR-100, Tiny-ImageNet, and ImageNet-Subset EFCIL benchmarks.
  arXiv  Detail & Related papers  (2022-12-16T02:43:52Z)
• Continual Learning with Guarantees via Weight Interval Constraints [18.791232422083265]
  We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. We show how to put bounds on forgetting by reformulating continual learning of a model as a continual contraction of its parameter space.
  arXiv  Detail & Related papers  (2022-06-16T08:28:37Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.