On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning

• URL: http://arxiv.org/abs/2603.09684v1
• Date: Tue, 10 Mar 2026 13:53:25 GMT
• Title: On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning
• Abstract summary: We show that forgetting is strongly influenced by the geometry and parameterization of the update subspace.<n>Our findings highlight update subspace design as a key factor in continual learning and offer practical guidance for selecting efficient adaptation strategies in sequential settings.
• Score: 14.815508281465272
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-efficient fine-tuning (PEFT) based on low-rank decomposition, such as LoRA, has become a standard for adapting large pretrained models. However, its behavior in sequential learning -- specifically regarding catastrophic forgetting -- remains insufficiently understood. In this work, we present an empirical study showing that forgetting is strongly influenced by the geometry and parameterization of the update subspace. While methods that restrict updates to small, shared matrix subspaces often suffer from task interference, tensor-based decompositions (e.g., LoRETTA) mitigate forgetting by capturing richer structural information within ultra-compact budgets, and structurally aligned parameterizations (e.g., WeGeFT) preserve pretrained representations. Our findings highlight update subspace design as a key factor in continual learning and offer practical guidance for selecting efficient adaptation strategies in sequential settings.

Related papers

• Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning [11.882528379148141]
  The magnitude of parameter updates are considered a key factor in continual learning.<n>We unify two representative update paradigms, frozen training and generalization training.<n>Experiments on deep neural networks demonstrate that this hybrid approach outperforms standard training strategies.
  arXiv  Detail & Related papers  (2026-02-24T11:35:15Z)
• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• Regularizing Subspace Redundancy of Low-Rank Adaptation [54.473090597164834]
  We propose ReSoRA, a method that explicitly models redundancy between mapping subspaces and adaptively Regularizes Subspace redundancy of Low-Rank Adaptation.<n>Our proposed method consistently facilitates existing state-of-the-art PETL methods across various backbones and datasets in vision-language retrieval and standard visual classification benchmarks.<n>As a training supervision, ReSoRA can be seamlessly integrated into existing approaches in a plug-and-play manner, with no additional inference costs.
  arXiv  Detail & Related papers  (2025-07-28T11:52:56Z)
• Weight Spectra Induced Efficient Model Adaptation [54.8615621415845]
  Fine-tuning large-scale foundation models incurs prohibitive computational costs.<n>We show that fine-tuning predominantly amplifies the top singular values while leaving the remainder largely intact.<n>We propose a novel method that leverages learnable rescaling of top singular directions.
  arXiv  Detail & Related papers  (2025-05-29T05:03:29Z)
• Efficient Federated Class-Incremental Learning of Pre-Trained Models via Task-agnostic Low-rank Residual Adaptation [22.454292668849035]
  Federated Task-agnostic Low-rank Residual Adaptation (Fed-TaLoRA)<n>We develop a novel residual weight update mechanism that ensures accurate knowledge consolidation with minimal overhead.<n>Our methodological innovations are attributed to three key strategies: task-agnostic adaptation, post-aggregation model calibration, and strategic placement of LoRA modules.
  arXiv  Detail & Related papers  (2025-05-18T09:19:13Z)
• Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations [50.010924231754856]
  Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence.<n>To overcome this, parameter-efficient fine-tuning (PEFT) methods like LoRA have emerged and are becoming a growing research focus.<n>We propose a generalization that extends matrix-based PEFT methods to higher-dimensional parameter spaces without compromising their structural properties.
  arXiv  Detail & Related papers  (2025-04-01T14:36:45Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
  Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method.<n>We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation.<n>Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
  arXiv  Detail & Related papers  (2024-10-05T06:59:50Z)
• Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation [12.07880147193174]
  We show that by leveraging the inherent low-dimensional structures of data and compressible dynamics within the model parameters, we can reap the benefits of over parameterization without the computational burdens. We demonstrate the effectiveness of this approach for deep low-rank matrix completion as well as fine-tuning language models.
  arXiv  Detail & Related papers  (2024-06-06T14:29:49Z)

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.