Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning

• URL: http://arxiv.org/abs/2605.28495v1
• Date: Wed, 27 May 2026 13:53:14 GMT
• Title: Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
• Abstract summary: Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning.<n>We propose textbfJanus-LoRA, a framework that restores this balance through two novel components.
• Score: 122.06915301391616
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ($A$ and $B$), creating a composite update to the full weight matrix through their interaction. To prevent catastrophic forgetting, this update should remain orthogonal to the task-specific subspace that contains previously learned knowledge. However, we identify that this composite update systematically violates this orthogonality, reintroducing interference and undermining stability. Furthermore, naively enforcing this orthogonality compromises plasticity, disrupting the delicate stability-plasticity trade-off. To resolve these issues, we propose \textbf{Janus-LoRA}, a framework that restores this balance through two novel components. Specifically, we first introduce Gradient Rectification, a closed-form solution that mathematically decouples LoRA's factor updates, enforcing orthogonality against the historical knowledge subspace identified by an efficient Online Estimation. Next, to enhance plasticity, we introduce a Decoupled Margin Loss that promotes feature-level separation by pushing new feature representations away from old ones, thus creating distinct, low-interference regions for new learning. Comprehensive experiments on challenging benchmarks demonstrate that by harmonizing parameter-level orthogonality with feature-level separation, Janus-LoRA achieves a superior balance and establishes new state-of-the-art performance.

Related papers

• Energy-Structured Low-Rank Adaptation for Continual Learning [78.5390284258307]
  We propose textbfEnergy-Concentrated and textbfEnergy-Ordered textbfLow-textbfRank textbfAdaptation (E$2$-LoRA)<n>By explicitly ordering and concentrating knowledge into leading ranks, E$2$-LoRA frees capacity for subsequent tasks.
  arXiv  Detail & Related papers  (2026-05-26T12:55:02Z)
• SR$^2$-LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning [3.9562791462574602]
  We present a novel perspective on catastrophic forgetting through the analysis of inter-layer relation drift.<n>We propose underlineSelf-underlineRectifying inter-layer underlineRelation Low-Rank Adaptation(SR$2$-LoRA)<n>Experiments on standard CIL benchmarks demonstrate that SR$2$-LoRA effectively mitigates catastrophic forgetting.
  arXiv  Detail & Related papers  (2026-05-08T08:14:50Z)
• 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)
• Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach [0.4870012761464388]
  Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining.<n>This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework to address these challenges.
  arXiv  Detail & Related papers  (2025-12-10T18:37:57Z)
• Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces [12.630494786258842]
  Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting.<n>We propose PS-LoRA, a framework designed to resolve conflicts by aligning updates within the optimization subspace.<n>Our approach employs a dual-regularization objective that penalizes conflicting directions and constrains magnitude deviations to ensure consistency with prior knowledge.
  arXiv  Detail & Related papers  (2025-11-28T15:34:36Z)
• SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting [68.00007494819798]
  Continual learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectively learning new tasks.<n> Gradient projection has emerged as an effective and popular paradigm in CL, where it partitions the gradient space of previously learned tasks into two subspaces.<n>New tasks are learned effectively within the minor subspace, thereby reducing interference with previously acquired knowledge.<n>Existing Gradient Projection methods struggle to achieve an optimal balance between plasticity and stability, as it is hard to appropriately partition the gradient space.
  arXiv  Detail & Related papers  (2025-05-28T13:57:56Z)
• FedHL: Federated Learning for Heterogeneous Low-Rank Adaptation via Unbiased Aggregation [6.5370850242187855]
  Federated Learning (FL) facilitates the fine-tuning of Foundation Models (FMs) using distributed data sources.<n>Low-Rank Adaptation (LoRA) gaining popularity due to its low communication costs and strong performance.<n>Existing methods lack formal convergence guarantees due to parameter truncation and biased gradient updates.
  arXiv  Detail & Related papers  (2025-05-24T04:12:12Z)
• Aggregation on Learnable Manifolds for Asynchronous Federated Optimization [3.8208848658169763]
  We introduce a geometric framework that casts aggregation as curve learning.<n>Within this, we propose AsyncBezier, which replaces linear aggregation with low-degree curvature components.<n>We show that these gains are preserved even when other methods are allocated a higher local compute budget.
  arXiv  Detail & Related papers  (2025-03-18T16:36:59Z)
• Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning [73.59672160329296]
  CKPD-FSCIL is a unified framework that unlocks the underutilized capacity of pretrained weights.<n>Our method consistently outperforms state-of-the-art approaches in both adaptability and knowledge retention.
  arXiv  Detail & Related papers  (2025-01-09T07:18:48Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)

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.