English
Related papers

Related papers: Unifying Regularisation Methods for Continual Lear…

200 papers

Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL methods, while…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Lars Möllenbrok , Behnood Rasti , Begüm Demir

This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…

Machine Learning · Computer Science 2018-10-19 Amir Erfan Eshratifar , David Eigen , Massoud Pedram

Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data. Artificial neural networks are no different in this regard and, despite having a level of implicit…

Machine Learning · Statistics 2022-05-26 Vincent Szolnoky , Viktor Andersson , Balazs Kulcsar , Rebecka Jörnsten

Biological synapses effortlessly balance memory retention and flexibility, yet artificial neural networks still struggle with the extremes of catastrophic forgetting and catastrophic remembering. Here, we introduce Metaplasticity from…

Machine Learning · Computer Science 2025-04-21 Djohan Bonnet , Kellian Cottart , Tifenn Hirtzlin , Tarcisius Januel , Thomas Dalgaty , Elisa Vianello , Damien Querlioz

In this work, we consider learning over multitask graphs, where each agent aims to estimate its own parameter vector. Although agents seek distinct objectives, collaboration among them can be beneficial in scenarios where relationships…

Machine Learning · Computer Science 2025-09-23 Yara Zgheib , Luca Calatroni , Marc Antonini , Roula Nassif

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Computation and Language · Computer Science 2025-02-18 Shezheng Song , Hao Xu , Jun Ma , Shasha Li , Long Peng , Qian Wan , Xiaodong Liu , Jie Yu

The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenges that exist at the algorithmic level. With growing interest…

Machine Learning · Computer Science 2025-03-04 Behraj Khan , Behroz Mirza , Nouman Durrani , Tahir Syed

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning…

Neural and Evolutionary Computing · Computer Science 2022-12-09 Francesco Lässig , Pau Vilimelis Aceituno , Martino Sorbaro , Benjamin F. Grewe

Deep state-space models (DSSMs) have gained popularity in recent years due to their potent modeling capacity for dynamic systems. However, existing DSSM works are limited to single-task modeling, which requires retraining with historical…

Machine Learning · Computer Science 2024-07-02 Yuanhang Zhang , Zhidi Lin , Yiyong Sun , Feng Yin , Carsten Fritsche

Weight decay is one of the standard tricks in the neural network toolbox, but the reasons for its regularization effect are poorly understood, and recent results have cast doubt on the traditional interpretation in terms of $L_2$…

Machine Learning · Computer Science 2018-10-30 Guodong Zhang , Chaoqi Wang , Bowen Xu , Roger Grosse

Synaptic pruning in biological brains removes weak connections to improve efficiency. In contrast, dropout regularization in artificial neural networks randomly deactivates neurons without considering activity-dependent pruning. We propose…

Machine Learning · Computer Science 2025-10-07 Gideon Vos , Liza van Eijk , Zoltan Sarnyai , Mostafa Rahimi Azghadi

Continual learning aims to acquire new tasks while preserving performance on previously learned ones, but most methods struggle with catastrophic forgetting. Existing approaches typically treat all layers uniformly, often trading stability…

Machine Learning · Computer Science 2025-12-29 Hengyi Wu , Zhenyi Wang , Heng Huang

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…

Machine Learning · Computer Science 2018-06-20 Risto Vuorio , Dong-Yeon Cho , Daejoong Kim , Jiwon Kim

Recent advances in semi-supervised learning have shown tremendous potential in overcoming a major barrier to the success of modern machine learning algorithms: access to vast amounts of human-labeled training data. Previous algorithms based…

Machine Learning · Computer Science 2019-11-22 Phi Vu Tran

Some novel strategies have recently been proposed for single hidden layer neural network training that set randomly the weights from input to hidden layer, while weights from hidden to output layer are analytically determined by…

Machine Learning · Computer Science 2015-08-26 R. Cancelliere , R. Deluca , M. Gai , P. Gallinari , L. Rubini

Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing…

Machine Learning · Statistics 2025-01-10 Verónica Álvarez , Santiago Mazuelas , Jose A. Lozano

We present the SCR framework for enhancing the training of graph neural networks (GNNs) with consistency regularization. Regularization is a set of strategies used in Machine Learning to reduce overfitting and improve the generalization…

Social and Information Networks · Computer Science 2022-06-14 Chenhui Zhang , Yufei He , Yukuo Cen , Zhenyu Hou , Wenzheng Feng , Yuxiao Dong , Xu Cheng , Hongyun Cai , Feng He , Jie Tang

Notable progress has been made in numerous fields of machine learning based on neural network-driven mutual information (MI) bounds. However, utilizing the conventional MI-based losses is often challenging due to their practical and…

Machine Learning · Computer Science 2022-06-22 Kwanghee Choi , Siyeong Lee

Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon learning new tasks. In many cases, such restrictions come at a…

Machine Learning · Computer Science 2024-06-21 Daniel Anthes , Sushrut Thorat , Peter König , Tim C. Kietzmann

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning. In recent years, numerous methods have been proposed for continual…

Machine Learning · Computer Science 2019-04-18 Gido M. van de Ven , Andreas S. Tolias