English
Related papers

Related papers: Frosting Weights for Better Continual Training

200 papers

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…

Machine Learning · Computer Science 2019-10-25 Xin Yao , Tianchi Huang , Chenglei Wu , Rui-Xiao Zhang , Lifeng Sun

Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years. Indeed, Deep Neural Networks are now the golden standard in domains as various as computer vision, natural language…

Machine Learning · Computer Science 2020-12-04 Vincent Gripon , Carlos Lassance , Ghouthi Boukli Hacene

Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We…

Machine Learning · Computer Science 2018-07-04 Jiayi Liu , Samarth Tripathi , Unmesh Kurup , Mohak Shah

Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly…

Machine Learning · Computer Science 2020-06-15 Seyed Iman Mirzadeh , Mehrdad Farajtabar , Razvan Pascanu , Hassan Ghasemzadeh

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial…

Machine Learning · Computer Science 2019-12-11 Mohammed Amer , Tomás Maul

Continual learning is a challenge for models with static architecture, as they fail to adapt to when data distributions evolve across tasks. We introduce a mathematical framework that jointly models architecture and weights in a Sobolev…

Machine Learning · Computer Science 2026-01-28 Allyson Hahn , Krishnan Raghavan

Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2019-11-19 Bowen Zhao , Xi Xiao , Guojun Gan , Bin Zhang , Shutao Xia

Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests…

Machine Learning · Computer Science 2026-03-06 Yunqin Zhu , Jun Jin

We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this setting is the so-called "catastrophic…

Machine Learning · Computer Science 2023-09-22 Christiaan Lamers , Rene Vidal , Nabil Belbachir , Niki van Stein , Thomas Baeck , Paris Giampouras

Recent work in continual learning has highlighted the beneficial effect of resampling weights in the last layer of a neural network (``zapping"). Although empirical results demonstrate the effectiveness of this approach, the underlying…

Machine Learning · Computer Science 2025-07-03 Lapo Frati , Neil Traft , Jeff Clune , Nick Cheney

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable…

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to…

Neural and Evolutionary Computing · Computer Science 2018-12-31 Yu Li , Zhongxiao Li , Lizhong Ding , Yijie Pan , Chao Huang , Yuhui Hu , Wei Chen , Xin Gao

While deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previously learned ones. Neuroscience studies, based on idealized…

Neural and Evolutionary Computing · Computer Science 2021-03-24 Axel Laborieux , Maxence Ernoult , Tifenn Hirtzlin , Damien Querlioz

We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Ahmet Iscen , Thomas Bird , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a…

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

A natural strategy for continual learning is to weigh a Bayesian ensemble of fixed functions. This suggests that if a (single) neural network could be interpreted as an ensemble, one could design effective algorithms that learn without…

Machine Learning · Computer Science 2025-02-28 Ari S. Benjamin , Christian Pehle , Kyle Daruwalla

Fine-tuning a pre-trained model on a downstream task often degrades its original capabilities, a phenomenon known as "catastrophic forgetting". This is especially an issue when one does not have access to the data and recipe used to develop…

Machine Learning · Computer Science 2025-06-13 Sunny Sanyal , Hayden Prairie , Rudrajit Das , Ali Kavis , Sujay Sanghavi

Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for many real-world…

Computer Vision and Pattern Recognition · Computer Science 2021-02-19 Sudhanshu Mittal , Silvio Galesso , Thomas Brox