paper-with-me

Papers

LoRA-Based Continual Learning with Constraints on Critical Parameter Changes

2025-04-18 · Shimou Ling, Liang Zhang, Jiangwei Zhao, Lili Pan, Hongliang Li

LoRA-based continual learning represents a promising avenue for leveraging pre-trained models in downstream continual learning tasks. Recent studies have shown that orthogonal LoRA tuning effectively mitigates forgetting. However, this work unveils that under orthogonal LoRA tuning, the critical parameters for pre-tasks still change notably after learning post-tasks. To address this problem, we directly propose freezing the most critical parameter matrices in the Vision Transformer (ViT) for pre-tasks before learning post-tasks. In addition, building on orthogonal LoRA tuning, we propose orthogonal LoRA composition (LoRAC) based on QR decomposition, which may further enhance the plasticity of our method. Elaborate ablation studies and extensive comparisons demonstrate the effectiveness of our proposed method. Our results indicate that our method achieves state-of-the-art (SOTA) performance on several well-known continual learning benchmarks. For instance, on the Split CIFAR-100 dataset, our method shows a 6.35\% improvement in accuracy and a 3.24\% reduction in forgetting compared to previous methods. Our code is available at https://github.com/learninginvision/LoRAC-IPC.

📄 PDF Abstract BibTeX arXiv:2504.13407

Code (1)

learninginvision/lorac-ipc 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

GEM-Style Constraints for PEFT with Dual Gradient Projection in LoRA

2026-01-05 · Brian Tekmen, Jason Yin, Qianqian Tong arxiv

Full fine-tuning of Large Language Models (LLMs) is computationally costly, motivating Continual Learning (CL) approaches that utilize parameter-efficient adapters. We revisit Gradient Episodic Memory (GEM) within the Lo…

Continual Learning

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation

2024-08-26 · Muhammad Fawi

This paper introduces CURLoRA, a novel approach to fine-tuning large language models (LLMs) that leverages CUR matrix decomposition in the context of Low-Rank Adaptation (LoRA). Our method addresses two critical challeng…

Continual Learning

Continual Learning with Low Rank Adaptation

2023-11-29 · Martin Wistuba, Prabhu Teja Sivaprasad, Lukas Balles, Giovanni Zappella

Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they struggle to retain that performance when the data characteristic…

Continual LearningIncremental Learning

Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning

2025-11-17 · Xinlan Wu, Bin Zhu, Feng Han, Pengkun Jiao 외 arxiv

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastr…

Semantic SimilarityContinual Learning

JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models

2026-04-17 · Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau, Marius Dragoi 외 arxiv

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgettin…

Continual Learning