English
Related papers

Related papers: Continual Learning with Query-Only Attention

200 papers

We propose a novel continual learning method called Residual Continual Learning (ResCL). Our method can prevent the catastrophic forgetting phenomenon in sequential learning of multiple tasks, without any source task information except the…

Machine Learning · Computer Science 2020-02-18 Janghyeon Lee , Donggyu Joo , Hyeong Gwon Hong , Junmo Kim

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically show that large…

Machine Learning · Computer Science 2025-10-29 Tiberiu Musat

Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to adapt to new tasks and perform significantly worse than…

Machine Learning · Computer Science 2025-03-27 Jiuqi Wang , Rohan Chandra , Shangtong Zhang

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

Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity)…

Machine Learning · Computer Science 2025-10-24 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual…

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

Machine Learning · Computer Science 2025-05-07 Yichen Li , Haozhao Wang , Wenchao Xu , Tianzhe Xiao , Hong Liu , Minzhu Tu , Yuying Wang , Xin Yang , Rui Zhang , Shui Yu , Song Guo , Ruixuan Li

Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…

Machine Learning · Computer Science 2017-12-18 Jack Lindsey

With the advent of state of the art nature-inspired pure attention based models i.e. transformers, and their success in natural language processing (NLP), their extension to machine vision (MV) tasks was inevitable and much felt.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-15 Abdul Mueed Hafiz , Shabir Ahmad Parah , Rouf Ul Alam Bhat

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty…

Neural and Evolutionary Computing · Computer Science 2019-03-15 Soheil Kolouri , Nicholas Ketz , Xinyun Zou , Jeffrey Krichmar , Praveen Pilly

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

Machine Learning · Computer Science 2019-11-01 Dushyant Rao , Francesco Visin , Andrei A. Rusu , Yee Whye Teh , Razvan Pascanu , Raia Hadsell

Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not…

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their…

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Machine Learning · Computer Science 2024-02-27 Yury Nahshan , Joseph Kampeas , Emir Haleva

The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments. Traditional learning-based models often suffer from performance degradation when encountering…

Machine Learning · Computer Science 2024-07-22 Xianda Chen , PakHin Tiu , Xu Han , Junjie Chen , Yuanfei Wu , Xinhu Zheng , Meixin Zhu

Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously…

Computation and Language · Computer Science 2021-01-11 Magdalena Biesialska , Katarzyna Biesialska , Marta R. Costa-jussà

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

In contrast to the natural capabilities of humans to learn new tasks in a sequential fashion, neural networks are known to suffer from catastrophic forgetting, where the model's performances on old tasks drop dramatically after being…

Machine Learning · Computer Science 2023-04-03 Sanghwan Kim , Lorenzo Noci , Antonio Orvieto , Thomas Hofmann
‹ Prev 1 8 9 10 Next ›