English

PLAN: Proactive Low-Rank Allocation for Continual Learning

Machine Learning 2025-10-27 v1 Artificial Intelligence

Abstract

Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline{P}roactive \underline{L}ow-rank \underline{A}llocatio\underline{N} (PLAN), a framework that extends Low-Rank Adaptation (LoRA) to enable efficient and interference-aware fine-tuning of large pre-trained models in CL settings. PLAN proactively manages the allocation of task-specific subspaces by introducing orthogonal basis vectors for each task and optimizing them through a perturbation-based strategy that minimizes conflicts with previously learned parameters. Furthermore, PLAN incorporates a novel selection mechanism that identifies and assigns basis vectors with minimal sensitivity to interference, reducing the risk of degrading past knowledge while maintaining efficient adaptation to new tasks. Empirical results on standard CL benchmarks demonstrate that PLAN consistently outperforms existing methods, establishing a new state-of-the-art for continual learning with foundation models.

Keywords

Cite

@article{arxiv.2510.21188,
  title  = {PLAN: Proactive Low-Rank Allocation for Continual Learning},
  author = {Xiequn Wang and Zhan Zhuang and Yu Zhang},
  journal= {arXiv preprint arXiv:2510.21188},
  year   = {2025}
}

Comments

accepted by ICCV 2025

R2 v1 2026-07-01T07:03:29.452Z