Adaptive Rank, Reduced Forgetting: Knowledge Retention in Continual Learning Vision-Language Models with Dynamic Rank-Selective LoRA

• URL: http://arxiv.org/abs/2412.01004v6
• Date: Wed, 08 Oct 2025 07:30:38 GMT
• Title: Adaptive Rank, Reduced Forgetting: Knowledge Retention in Continual Learning Vision-Language Models with Dynamic Rank-Selective LoRA
• Authors: Haodong Lu, Chongyang Zhao, Jason Xue, Lina Yao, Kristen Moore, Dong Gong,
• Abstract summary: We study low-rank learning and analyze how LoRA ranks and placements affect learning and forgetting.<n>A higher-rank LoRA improves task learning (plasticity) but increases forgetting, while a lower-rank LoRA enhances stability but limits adaptation.<n>Motivated by this, we propose Continual Dynamic Rank-Selective LoRA (CoDyRA), which continually updates PTMs with LoRA adapters of adaptively optimized ranks.
• Score: 26.079123341965687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning (CL) aims to accumulate knowledge from sequential tasks without catastrophic forgetting. Vision-language models such as CLIP, with strong generalization, are widely used for CL. Existing methods often adapt isolated PTM components, increasing inference complexity and limiting model improvement, or rely on replay, stored data, or assumptions, leading to high costs and limited applicability. To advance models as continual learners, we explore CL through natural and efficient PTM updates rather than complex task-specific additions. We study continual low-rank learning and analyze how LoRA ranks and placements affect learning and forgetting. A higher-rank LoRA improves task learning (plasticity) but increases forgetting, while a lower-rank LoRA enhances stability but limits adaptation. We observe a plasticity-stability balance tied to rank across parameters and tasks, with moderately small ranks maximizing CL benefits. Motivated by this, we propose Continual Dynamic Rank-Selective LoRA (CoDyRA), which continually updates PTMs with LoRA adapters of adaptively optimized ranks. The new-task objective drives learning, while sparsity-promoting regularization minimizes ranks to reduce interference and forgetting, achieving a balance tailored to each parameter and task. Although all parameters are updated, the minimized ranks keep the model close to its prior state while enabling effective new-task learning. CoDyRA performs efficient CL as a sequence of LoRA-based updates without storing past data or relying on assumptions, preserving the original model architecture and adding no inference overhead. Experiments show CoDyRA improves new representations while retaining old knowledge, achieving state-of-the-art results. Code is available at https://github.com/jeff024/codyra.

Related papers

• Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning [82.30237756328596]
  Low-Rank Adaptation (LoRA) has gained increasing attention in Continual Learning (CL)<n>Several LoRA-based CL methods reduce interference across tasks by separating their update spaces.<n>LoDA performs a task-driven decomposition to build general and truly task-specific LoRA subspaces.
  arXiv  Detail & Related papers  (2026-02-27T02:31:00Z)
• LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules [10.00294036303927]
  We introduce LoRA-Squeeze, a simple and efficient methodology that aims to improve standard LoRA learning.<n>Our approach posits that it is better to first learn an expressive, higher-rank solution and then compress it, rather than learning a constrained, low-rank solution directly.
  arXiv  Detail & Related papers  (2026-02-11T16:19:58Z)
• Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning [48.66442009036754]
  Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model fine-tuning.<n>In this work, we re-evaluate four representative LoRA variants alongside vanilla LoRA.<n>We find that different LoRA methods favor distinct learning rate ranges.
  arXiv  Detail & Related papers  (2026-02-04T19:36:20Z)
• 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)
• CLA: Latent Alignment for Online Continual Self-Supervised Learning [53.52783900926569]
  We introduce Continual Latent Alignment (CLA), a novel SSL strategy for Online CL.<n>Our CLA is able to speed up the convergence of the training process in the online scenario, outperforming state-of-the-art approaches under the same computational budget.<n>We also discovered that using CLA as a pretraining protocol in the early stages of pretraining leads to a better final performance when compared to a full i.i.d. pretraining.
  arXiv  Detail & Related papers  (2025-07-14T16:23:39Z)
• Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning [11.50324946279326]
  Contrastive Language-Image Pre-trained model (CLIP) exhibiting strong capabilities across various downstream tasks.<n>We analyze the variations in the modality gap during the fine-tuning of vision-language pre-trained models.<n>We propose a simple yet effective method, MG-CLIP, that improves CLIP's performance in class-incremental learning.
  arXiv  Detail & Related papers  (2025-07-12T02:28:42Z)
• Diffusion Guidance Is a Controllable Policy Improvement Operator [98.11511661904618]
  CFGRL is trained with the simplicity of supervised learning, yet can further improve on the policies in the data.<n>On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance.
  arXiv  Detail & Related papers  (2025-05-29T14:06:50Z)
• Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation [19.48677836920734]
  Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL)<n>We introduce PEARL, a rehearsal-free CL framework that entails dynamic rank allocation for LoRA components during CL training.
  arXiv  Detail & Related papers  (2025-05-17T13:19:01Z)
• Enhancing knowledge retention for continual learning with domain-specific adapters and features gating [4.637185817866919]
  Continual learning empowers models to learn from a continuous stream of data while preserving previously acquired knowledge. We propose a new approach that integrates adapters within the self-attention mechanisms of Vision Transformers to enhance knowledge retention when sequentially adding datasets from different domains.
  arXiv  Detail & Related papers  (2025-04-11T15:20:08Z)
• FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning [19.068489119024388]
  Continual learning has emerged as a promising approach to leverage pre-trained models for sequential tasks.<n>Many existing CL methods incrementally store additional learned structures, such as Low-Rank Adaptation (LoRA) adapters or prompts.<n>We propose FM-LoRA, a novel and efficient low-rank adaptation method that integrates both a dynamic rank selector (DRS) and dynamic meta-prompting (DMP)
  arXiv  Detail & Related papers  (2025-04-09T19:36:18Z)
• C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models [26.560293264523903]
  Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision.<n>We propose Continual Low-Rank Adaptation (C-LoRA), a novel extension of LoRA for continual learning.<n>C-LoRA uses a learnable routing matrix to dynamically manage parameter updates across tasks.
  arXiv  Detail & Related papers  (2025-02-25T07:35:36Z)
• SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs [4.194295877935867]
  We propose a lightweight continual learning framework for large language models (LLMs) Our method achieves high knowledge retention in both task-incremental and domain-incremental continual learning setups. Experiments on the SuperGLUE benchmark demonstrate that our PCA-based prompt tuning combined with LoRA maintains full knowledge retention while improving accuracy, utilizing only 1% of the model's parameters.
  arXiv  Detail & Related papers  (2025-02-05T06:11:55Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Aligning Instruction Tuning with Pre-training [81.4748965653345]
  We propose Aligning Instruction Tuning with Pre-training (AITP) to align instruction tuning with pre-training distributions. We show consistent performance improvements with AITP on three fully open large language models (LLMs) across eight benchmarks.
  arXiv  Detail & Related papers  (2025-01-16T08:27:40Z)
• Replay-Free Continual Low-Rank Adaptation with Dynamic Memory [62.85596937435928]
  We revisit continual learning, which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time.<n>Recent studies highlight a crossover between CL techniques and parameter-efficient fine-tuning.<n>We propose a novel PEFT-CL method called Dual Low-Rank Adaptation (DualLoRA)
  arXiv  Detail & Related papers  (2024-11-01T14:28:39Z)
• Temporal-Difference Variational Continual Learning [89.32940051152782]
  A crucial capability of Machine Learning models in real-world applications is the ability to continuously learn new tasks. In Continual Learning settings, models often struggle to balance learning new tasks with retaining previous knowledge. We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning [22.13331870720021]
  We propose a beyond prompt learning approach to the RFCL task, called Continual Adapter (C-ADA) C-ADA flexibly extends specific weights in CAL to learn new knowledge for each task and freezes old weights to preserve prior knowledge. Our approach achieves significantly improved performance and training speed, outperforming the current state-of-the-art (SOTA) method.
  arXiv  Detail & Related papers  (2024-07-14T17:40:40Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
  Domain-Class Incremental Learning is a realistic but challenging continual learning scenario. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead. We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
  arXiv  Detail & Related papers  (2024-07-07T12:19:37Z)
• What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights [67.72413262980272]
  Severe data imbalance naturally exists among web-scale vision-language datasets. We find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning. The robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts.
  arXiv  Detail & Related papers  (2024-05-31T17:57:24Z)
• Investigating Continual Pretraining in Large Language Models: Insights and Implications [9.660013084324817]
  Continual learning in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies. We introduce a new benchmark designed to measure the adaptability of LLMs to changing pretraining data landscapes. Our findings uncover several key insights: (i) continual pretraining consistently improves 1.5B models studied in this work and is also superior to domain adaptation, (ii) larger models always achieve better perplexity than smaller ones when continually pretrained on the same corpus, (iii) smaller models are particularly sensitive to continual pretraining, showing the most significant rates of both learning and
  arXiv  Detail & Related papers  (2024-02-27T10:47:24Z)
• Sparse Low-rank Adaptation of Pre-trained Language Models [79.74094517030035]
  We introduce sparse low-rank adaptation (SoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process. Our approach strengthens the representation power of LoRA by initializing it with a higher rank, while efficiently taming a temporarily increased number of parameters. Our experimental results demonstrate that SoRA can outperform other baselines even with 70% retained parameters and 70% training time.
  arXiv  Detail & Related papers  (2023-11-20T11:56:25Z)
• Continual Learners are Incremental Model Generalizers [70.34479702177988]
  This paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. We find that the transfer quality of the representation often increases gradually without noticeable degradation in fine-tuning performance. We propose a new fine-tuning scheme, GLobal Attention Discretization (GLAD), that preserves rich task-generic representation during solving downstream tasks.
  arXiv  Detail & Related papers  (2023-06-21T05:26:28Z)
• CLIPood: Generalizing CLIP to Out-of-Distributions [73.86353105017076]
  Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on unseen test data. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.
  arXiv  Detail & Related papers  (2023-02-02T04:27:54Z)
• Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations [22.289830907729705]
  Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one. Main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
  arXiv  Detail & Related papers  (2022-11-10T05:29:43Z)
• Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis [96.53859361560505]
  Aspect-based Sentiment Analysis (ABSA) aims to determine the sentiment polarity towards an aspect. There always exists severe domain shift between the pretraining and downstream ABSA datasets. We introduce a unified alignment pretraining framework into the vanilla pretrain-finetune pipeline.
  arXiv  Detail & Related papers  (2021-10-26T04:03:45Z)

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.