English
Related papers

Related papers: Improving Representational Continuity via Continue…

200 papers

Standard large language model training can create models that produce outputs their trainer deems unacceptable in deployment. The probability of these outputs can be reduced using methods such as LLM unlearning. However, unlearning a set of…

Machine Learning · Computer Science 2026-02-12 Lev McKinney , Anvith Thudi , Juhan Bae , Tara Rezaei , Nicolas Papernot , Sheila A. McIlraith , Roger Grosse

We introduce a novel continual learning method based on multifidelity deep neural networks. This method learns the correlation between the output of previously trained models and the desired output of the model on the current training…

Numerical Analysis · Mathematics 2024-07-01 Amanda Howard , Yucheng Fu , Panos Stinis

Inspired by the \emph{Well-initialized Lottery Ticket Hypothesis (WLTH)}, we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework for continual learning that leverages soft, real-valued subnetworks over a frozen pre-trained…

Machine Learning · Computer Science 2026-04-29 Haeyong Kang , Chang D. Yoo

Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of…

Machine Learning · Computer Science 2024-04-24 Da-Wei Zhou , Hai-Long Sun , Jingyi Ning , Han-Jia Ye , De-Chuan Zhan

Continual learning empowers models to learn from a continuous stream of data while preserving previously acquired knowledge, effectively addressing the challenge of catastrophic forgetting. In this study, we propose a new approach that…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Mohamed Abbas Hedjazi , Oussama Hadjerci , Adel Hafiane

We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrophic forgetting in neural networks, recent works on…

Computer Vision and Pattern Recognition · Computer Science 2022-07-07 Stanisław Pawlak , Filip Szatkowski , Michał Bortkiewicz , Jan Dubiński , Tomasz Trzciński

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by…

Machine Learning · Statistics 2014-10-22 Saahil Ognawala , Justin Bayer

Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user.…

Machine Learning · Computer Science 2023-11-22 Sara Babakniya , Zalan Fabian , Chaoyang He , Mahdi Soltanolkotabi , Salman Avestimehr

Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a…

Machine Learning · Computer Science 2019-06-26 Shixian Wen , Laurent Itti

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…

Computation and Language · Computer Science 2019-06-03 Alexandra Chronopoulou , Christos Baziotis , Alexandros Potamianos

Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the ubiquitous use-case…

Machine Learning · Computer Science 2026-05-25 Lukas Thede , Stefan Winzeck , Zeynep Akata , Jonathan Richard Schwarz

The two-stage fine-tuning (FT) method, linear probing (LP) then fine-tuning (LP-FT), outperforms linear probing and FT alone. This holds true for both in-distribution (ID) and out-of-distribution (OOD) data. One key reason for its success…

Machine Learning · Computer Science 2024-10-23 Akiyoshi Tomihari , Issei Sato

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…

Machine Learning · Computer Science 2021-03-25 Andrea Cossu , Antonio Carta , Davide Bacciu

Continual learning tries to learn new tasks without forgetting previously learned ones. In reality, most of the existing artificial neural network(ANN) models fail, while humans do the same by remembering previous works throughout their…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Subhankar Ghosh

Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…

Machine Learning · Computer Science 2023-06-29 Qiao Gu , Dongsub Shim , Florian Shkurti

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor…

Machine Learning · Computer Science 2021-03-18 Hlynur Davíð Hlynsson , Merlin Schüler , Robin Schiewer , Tobias Glasmachers , Laurenz Wiskott

The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Sayna Ebrahimi , Suzanne Petryk , Akash Gokul , William Gan , Joseph E. Gonzalez , Marcus Rohrbach , Trevor Darrell

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM,…

Machine Learning · Computer Science 2026-04-16 Mark Rofin , Aditya Varre , Nicolas Flammarion

How to adapt a pre-trained model continuously for sequential tasks with different prediction class labels and domains and finally learn a generalizable model across diverse tasks is a long-lasting challenge. Continual learning (CL) has…

Machine Learning · Computer Science 2025-04-15 Xiaobing Yu , Jin Yang , Xiao Wu , Peijie Qiu , Xiaofeng Liu

LiDAR place recognition plays a crucial role in SLAM, robot navigation, and autonomous driving. However, existing LiDAR place recognition methods often struggle to adapt to new environments without forgetting previously learned knowledge, a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Xufei Wang , Junqiao Zhao , Siyue Tao , Qiwen Gu , Wonbong Kim , Tiantian Feng