# SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

arXiv: https://arxiv.org/abs/2501.13198 · HTML: https://mlsanity.com/paper/2501.13198/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 22 Jan 2025.

## Builds on (most cited first, 30 of 36)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks](https://mlsanity.com/paper/2110.06296/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Controlling Text-to-Image Diffusion by Orthogonal Finetuning](https://mlsanity.com/paper/2306.07280/) (2023)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [A Unified Continual Learning Framework with General Parameter-Efficient Tuning](https://mlsanity.com/paper/2303.10070/) (2023)
- [Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality](https://mlsanity.com/paper/2310.07234/) (2023)
- [Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild](https://mlsanity.com/paper/1903.12648/) (2019)
- [GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning](https://mlsanity.com/paper/2111.11210/) (2021)
- [Knowledge is a Region in Weight Space for Fine-tuned Language Models](https://mlsanity.com/paper/2302.04863/) (2023)
- [Model Zoo: A Growing "Brain" That Learns Continually](https://mlsanity.com/paper/2106.03027/) (2021)

## Built on by (most cited first, 30 of 63)

- [Merge before Forget: A Single LoRA Continual Learning via Continual Merging](https://mlsanity.com/paper/2512.23017/) (2025)
- [Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR](https://mlsanity.com/paper/2603.24840/) (2026)
- [Continuous Subspace Optimization for Continual Learning](https://mlsanity.com/paper/2505.11816/) (2025)
- [Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning](https://mlsanity.com/paper/2603.00191/) (2026)
- [Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning](https://mlsanity.com/paper/2506.05985/) (2025)
- [Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning](https://mlsanity.com/paper/2505.22389/) (2025)
- [PLAN: Proactive Low-Rank Allocation for Continual Learning](https://mlsanity.com/paper/2510.21188/) (2025)
- [Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection](https://mlsanity.com/paper/2602.07892/) (2026)
- [Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts](https://mlsanity.com/paper/2506.21035/) (2025)
- [MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts](https://mlsanity.com/paper/2510.13500/) (2025)
- [FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling](https://mlsanity.com/paper/2501.19122/) (2025)
- [FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning](https://mlsanity.com/paper/2504.08823/) (2025)
- [Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives](https://mlsanity.com/paper/2505.15222/) (2025)
- [MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition](https://mlsanity.com/paper/2511.06225/) (2025)
- [When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters](https://mlsanity.com/paper/2602.21977/) (2026)
- [Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection](https://mlsanity.com/paper/2603.19145/) (2026)
- [C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models](https://mlsanity.com/paper/2502.17920/) (2025)
- [Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models](https://mlsanity.com/paper/2508.19564/) (2025)
- [Policy Compatible Skill Incremental Learning via Lazy Learning Interface](https://mlsanity.com/paper/2509.20612/) (2025)
- [Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts](https://mlsanity.com/paper/2602.03473/) (2026)
- [Revisiting Weight Regularization for Low-Rank Continual Learning](https://mlsanity.com/paper/2602.17559/) (2026)
- [Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings](https://mlsanity.com/paper/2502.11609/) (2025)
- [Holistic Continual Learning under Concept Drift with Adaptive Memory Realignment](https://mlsanity.com/paper/2507.02310/) (2025)
- [Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning](https://mlsanity.com/paper/2508.11673/) (2025)
- [Domain Generalizable Continual Learning](https://mlsanity.com/paper/2510.16914/) (2025)
- [Continual Low-Rank Adapters for LLM-based Generative Recommender Systems](https://mlsanity.com/paper/2510.25093/) (2025)
- [FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning](https://mlsanity.com/paper/2602.01976/) (2026)
- [tLoRA: Efficient Multi-LoRA Training with Elastic Shared Super-Models](https://mlsanity.com/paper/2602.07263/) (2026)
- [Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning](https://mlsanity.com/paper/2606.01379/) (2026)
- [Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning](https://mlsanity.com/paper/2505.12318/) (2025)

## Abstract (arXiv)

Continual Learning (CL) with foundation models has recently emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks. However, existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks, which poses significant scalability challenges as the number of tasks grows. To address these limitations, 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. Our empirical and theoretical analysis reveals that SD-LoRA tends to follow a low-loss trajectory and converges to an overlapping low-loss region for all learned tasks, resulting in an excellent stability-plasticity trade-off. Building upon these insights, we introduce two variants of SD-LoRA with further improved parameter efficiency. All parameters of SD-LoRAs can be end-to-end optimized for CL objectives. Meanwhile, they support efficient inference by allowing direct evaluation with the finally trained model, obviating the need for component selection. Extensive experiments across multiple CL benchmarks and foundation models consistently validate the effectiveness of SD-LoRA. The code is available at https://github.com/WuYichen-97/SD-Lora-CL.