English
Related papers

Related papers: Take Only What You Need: Rank Minimization as an I…

200 papers

The principle underlying most existing continual learning (CL) methods is to prioritize stability by penalizing changes in parameters crucial to old tasks, while allowing for plasticity in other parameters. The importance of weights for…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Fei Yang , Kai Wang , Joost van de Weijer

Continual adaptation of deep generative models holds tremendous potential and critical importance, given their rapid and expanding usage in text and vision based applications. Incremental training, however, remains highly challenging due to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Victor Enescu , Hichem Sahbi

In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting. The principal target of our approach is the automatic…

Machine Learning · Computer Science 2021-01-19 Ammar Shaker , Shujian Yu , Francesco Alesiani

Plasticity Loss is an increasingly important phenomenon that refers to the empirical observation that as a neural network is continually trained on a sequence of changing tasks, its ability to adapt to a new task diminishes over time. We…

Machine Learning · Computer Science 2025-09-30 Vivek F. Farias , Adam D. Jozefiak

The dilemma between plasticity and stability presents a significant challenge in Incremental Learning (IL), especially in the exemplar-free scenario where accessing old-task samples is strictly prohibited during the learning of a new task.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Wenju Sun , Qingyong Li , Wen Wang , Yangli-ao Geng

Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights, dramatically reducing trainable parameters and memory. However, there is still a gap between full training with low-rank projections…

The ability of neural networks to continuously learn and adapt to new tasks while retaining prior knowledge is crucial for many applications. However, current neural networks tend to forget previously learned tasks when trained on new ones,…

Computer Vision and Pattern Recognition · Computer Science 2020-05-04 Sinan Özgür Özgün , Anne-Marie Rickmann , Abhijit Guha Roy , Christian Wachinger

Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime…

Machine Learning · Computer Science 2026-04-28 Paul-Tiberiu Iordache , Elena Burceanu

Low-Rank Adaptation (LoRA) is the dominant parameter-efficient fine-tuning method due to its favorable compute-performance trade-off, yet it suffers from catastrophic forgetting. We study forgetting through a tractable _mean-field…

Machine Learning · Computer Science 2026-05-14 Hugo Koubbi , Louis Hernandez , Matthieu Boussard

Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank…

Machine Learning · Computer Science 2024-11-05 Andi Han , Jiaxiang Li , Wei Huang , Mingyi Hong , Akiko Takeda , Pratik Jawanpuria , Bamdev Mishra

Online Continual Learning (CL) solves the problem of learning the ever-emerging new classification tasks from a continuous data stream. Unlike its offline counterpart, in online CL, the training data can only be seen once. Most existing…

Machine Learning · Computer Science 2024-04-02 Maorong Wang , Nicolas Michel , Ling Xiao , Toshihiko Yamasaki

Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Tao Feng , Hangjie Yuan , Mang Wang , Ziyuan Huang , Ang Bian , Jianzhou Zhang

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…

Machine Learning · Computer Science 2026-02-02 Yuxuan Li , Qijun He , Mingqi Yuan , Wen-Tse Chen , Jeff Schneider , Jiayu Chen

Continual learning algorithms aim to learn from a sequence of tasks. In order to avoid catastrophic forgetting, most existing approaches rely on heuristics and do not provide computable learning guarantees. In this paper, we introduce…

Machine Learning · Computer Science 2026-02-27 Jacob Comeau , Mathieu Bazinet , Pascal Germain , Cem Subakan

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of…

Machine Learning · Computer Science 2026-03-31 Ashish Pandey

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer,…

Machine Learning · Computer Science 2020-07-07 Ron Amit , Ron Meir , Kamil Ciosek

Deep Neural Networks (DNNs) have achieved remarkable success in addressing many previously unsolvable tasks. However, the storage and computational requirements associated with DNNs pose a challenge for deploying these trained models on…

Machine Learning · Computer Science 2024-10-18 Xitong Zhang , Ismail R. Alkhouri , Rongrong Wang

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Computation and Language · Computer Science 2025-05-02 Xiao Zhang , Kangsheng Wang , Tianyu Hu , Huimin Ma

Parameter-Efficient Fine-Tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), are indispensable for efficiently customizing Large Language Models (LLMs). However, vanilla LoRA suffers from slow convergence speed and knowledge…

Machine Learning · Computer Science 2025-11-03 Minrui Luo , Fuhang Kuang , Yu Wang , Zirui Liu , Tianxing He

We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily focus on regularizing model updates to preserve old…

Machine Learning · Computer Science 2025-06-03 Leila Mahmoodi , Peyman Moghadam , Munawar Hayat , Christian Simon , Mehrtash Harandi