paper-with-me

홈 › Papers

Orthogonal Subspace Learning for Language Model Continual Learning

2023-10-22 · Xiao Wang, Tianze Chen, Qiming Ge, Han Xia, Rong Bao, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their performance degrades in scenarios where multiple tasks are encountered sequentially, also known as catastrophic forgetting. In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks. Specifically, O-LoRA learns tasks in different (low-rank) vector subspaces that are kept orthogonal to each other in order to minimize interference. Our method induces only marginal additional parameter costs and requires no user data storage for replay. Experimental results on continual learning benchmarks show that our method outperforms state-of-the-art methods. Furthermore, compared to previous approaches, our method excels in preserving the generalization ability of LLMs on unseen tasks.

📄 PDF Abstract BibTeX arXiv:2310.14152

Code (1)

cmnfriend/o-lora 공식 구현 pytorch

Tasks

Continual LearningLanguage ModelingLanguage Modellingmodel

Similar Papers 제목 키워드 기반

Orthogonal Low-rank Adaptation in Lie Groups for Continual Learning of Large Language Models

2025-09-07 · Kefan Cao, Shuaicheng Wu arxiv

Large language models (LLMs) suffer from catastrophic forgetting in sequential multi-task learning. Existing parameter regularization methods (e.g., O-LoRA, N-LoRA) mitigate interference via low-rank subspace orthogonali…

Multi-Task LearningContinual Learning

Budget-Adaptive Adapter Tuning in Orthogonal Subspaces for Continual Learning in LLMs

2025-05-28 · Zhiyi Wan, Wanrou Du, Liang Li, Miao Pan 외

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning (CL) scenarios, where performance on previously learned tasks degrades severely while training on sequentially arriving tasks. …

Continual Learning

Continual Learning in Low-rank Orthogonal Subspaces

2020-10-22 · NeurIPS 2020 12 · Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL use…

Continual Learning

GopGAN: Gradients Orthogonal Projection Generative Adversarial Network With Continual Learning

2021-07-16 · IEEE Transactions on Neural Networks and Learning Systems 2021 7 · Xiaobin Li; Weiqiang Wang

The generative adversarial networks (GANs) in continual learning suffer from catastrophic forgetting. In continual learning, GANs tend to forget about previous generation tasks and only remember the tasks they just learn…

Continual LearningGenerative Adversarial Network

Class Gradient Projection For Continual Learning

2023-11-25 · Cheng Chen, Ji Zhang, Jingkuan Song, Lianli Gao

Catastrophic forgetting is one of the most critical challenges in Continual Learning (CL). Recent approaches tackle this problem by projecting the gradient update orthogonal to the gradient subspace of existing tasks. Wh…

Continual LearningContrastive Learning