English
Related papers

Related papers: ScrollNet: Dynamic Weight Importance for Continual…

200 papers

Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much…

Computation and Language · Computer Science 2021-06-14 Yufan Huang , Yanzhe Zhang , Jiaao Chen , Xuezhi Wang , Diyi Yang

Continual learning (CL) is crucial for evaluating adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they…

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

Generative flow networks (GFlowNets), as an emerging technique, can be used as an alternative to reinforcement learning for exploratory control tasks. GFlowNet aims to generate distribution proportional to the rewards over terminating…

Machine Learning · Computer Science 2023-03-07 Yinchuan Li , Shuang Luo , Haozhi Wang , Jianye Hao

Continual learning (CL) aims to help deep neural networks learn new knowledge while retaining what has been learned. Owing to their powerful generalizability, pre-trained vision-language models such as Contrastive Language-Image…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Saurav Jha , Dong Gong , Lina Yao

Deep neural networks (DNN) have shown great capacity of modeling a dynamical system; nevertheless, they usually do not obey physics constraints such as conservation laws. This paper proposes a new learning framework named ConCerNet to…

Machine Learning · Computer Science 2023-07-20 Wang Zhang , Tsui-Wei Weng , Subhro Das , Alexandre Megretski , Luca Daniel , Lam M. Nguyen

The challenging deployment of compute- and memory-intensive methods from Deep Neural Network (DNN)-based Continual Learning (CL) underscores the critical need for a paradigm shift towards more efficient approaches. Neuromorphic Continual…

Neural and Evolutionary Computing · Computer Science 2025-07-22 Mishal Fatima Minhas , Rachmad Vidya Wicaksana Putra , Falah Awwad , Osman Hasan , Muhammad Shafique

Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Huan Wang , Can Qin , Yulun Zhang , Yun Fu

Continual Learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectively learning new tasks. Gradient projection has emerged as…

Machine Learning · Computer Science 2025-06-12 Haomiao Qiu , Miao Zhang , Ziyue Qiao , Weili Guan , Min Zhang , Liqiang Nie

Continual learning requires incremental compatibility with a sequence of tasks. However, the design of model architecture remains an open question: In general, learning all tasks with a shared set of parameters suffers from severe…

Machine Learning · Computer Science 2022-07-15 Liyuan Wang , Xingxing Zhang , Qian Li , Jun Zhu , Yi Zhong

Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility,…

Machine Learning · Computer Science 2025-01-03 Vinod Kumar Chauhan , Jiandong Zhou , Ping Lu , Soheila Molaei , David A. Clifton

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Machine Learning · Computer Science 2026-04-01 Yining Lu , Zilong Wang , Shiyang Li , Xin Liu , Changlong Yu , Qingyu Yin , Zhan Shi , Zixuan Zhang , Meng Jiang

Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…

Machine Learning · Computer Science 2025-02-18 Huanxuan Liao , Shizhu He , Yupu Hao , Jun Zhao , Kang Liu

Weight-sharing is ubiquitous in deep learning. Motivated by this, we propose a "weight-sharing regularization" penalty on the weights $w \in \mathbb{R}^d$ of a neural network, defined as $\mathcal{R}(w) = \frac{1}{d - 1}\sum_{i > j}^d |w_i…

Machine Learning · Computer Science 2024-03-12 Mehran Shakerinava , Motahareh Sohrabi , Siamak Ravanbakhsh , Simon Lacoste-Julien

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states.…

Machine Learning · Computer Science 2021-01-07 Hieu Pham , Quoc V. Le

The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream…

Machine Learning · Computer Science 2025-05-20 Liangzu Peng , Juan Elenter , Joshua Agterberg , Alejandro Ribeiro , René Vidal

Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have a similar theme: a set of intuitive and manually designed policies that are generic and fixed (e.g. SIFT or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Huiyu Wang , Aniruddha Kembhavi , Ali Farhadi , Alan Yuille , Mohammad Rastegari

Example weighting algorithm is an effective solution to the training bias problem, however, most previous typical methods are usually limited to human knowledge and require laborious tuning of hyperparameters. In this paper, we propose a…

Machine Learning · Computer Science 2019-11-27 Zhenmao Li , Yichao Wu , Ken Chen , Yudong Wu , Shunfeng Zhou , Jiaheng Liu , Junjie Yan

Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcoming CF. Some work has also been done on KT when the tasks are…

Computation and Language · Computer Science 2023-10-17 Zixuan Ke , Bing Liu , Wenhan Xiong , Asli Celikyilmaz , Haoran Li

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