paper-with-me

Papers

Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation

2024-11-08 · Xiwen Wei, Guihong Li, Radu Marculescu

Catastrophic forgetting is a significant challenge in online continual learning (OCL), especially for non-stationary data streams that do not have well-defined task boundaries. This challenge is exacerbated by the memory constraints and privacy concerns inherent in rehearsal buffers. To tackle catastrophic forgetting, in this paper, we introduce Online-LoRA, a novel framework for task-free OCL. Online-LoRA allows to finetune pre-trained Vision Transformer (ViT) models in real-time to address the limitations of rehearsal buffers and leverage pre-trained models' performance benefits. As the main contribution, our approach features a novel online weight regularization strategy to identify and consolidate important model parameters. Moreover, Online-LoRA leverages the training dynamics of loss values to enable the automatic recognition of the data distribution shifts. Extensive experiments across many task-free OCL scenarios and benchmark datasets (including CIFAR-100, ImageNet-R, ImageNet-S, CUB-200 and CORe50) demonstrate that Online-LoRA can be robustly adapted to various ViT architectures, while achieving better performance compared to SOTA methods. Our code will be publicly available at: https://github.com/Christina200/Online-LoRA-official.git.

📄 PDF Abstract BibTeX arXiv:2411.05663

Code (1)

christina200/online-lora-official 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

2025-10-15 · Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay 외 arxiv

On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile …

Safe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Art

2026-01-08 · Timofey Tomashevskiy arxiv

This work provides a state-of-the-art survey of continual safe online reinforcement learning (COSRL) methods. We discuss theoretical aspects, challenges, and open questions in building continual online safe reinforcement…

Reinforcement LearningContinual Learning

Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task

2024-05-28 · Huiping Zhuang, Di Fang, Kai Tong, Yuchen Liu 외

In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come…

Autonomous DrivingContinual LearningExemplar-Free

Rehearsal-free and Task-free Online Continual Learning With Contrastive Prompt

2025-10-01 · Aopeng Wang, Ke Deng, Yongli Ren, Jun Luo arxiv

The main challenge of continual learning is \textit{catastrophic forgetting}. Because of processing data in one pass, online continual learning (OCL) is one of the most difficult continual learning scenarios. To address …

Continual Learning

Is Prompt Selection Necessary for Task-Free Online Continual Learning?

2026-04-06 · Seoyoung Park, Haemin Lee, Hankook Lee arxiv

Task-free online continual learning has recently emerged as a realistic paradigm for addressing continual learning in dynamic, real-world environments, where data arrive in a non-stationary stream without clear task boun…

Continual Learning