English
Related papers

Related papers: Fine-Grained Gradient Restriction: A Simple Approa…

200 papers

The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance…

Machine Learning · Computer Science 2021-03-18 Gobinda Saha , Isha Garg , Kaushik Roy

Gradient Episodic Memory is indeed a novel method for continual learning, which solves new problems quickly without forgetting previously acquired knowledge. However, in the process of studying the paper, we found there were some problems…

Machine Learning · Computer Science 2021-07-16 Wei Zhou , Yiying Li

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher…

Machine Learning · Computer Science 2026-01-27 Chao-Hong Tan , Qian Chen , Wen Wang , Yukun Ma , Chong Zhang , Chong Deng , Qinglin Zhang , Xiangang Li , Jieping Ye

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Songze Li , Mingyu Gao , Tonghua Su , Xu-Yao Zhang , Zhongjie Wang

Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…

Machine Learning · Computer Science 2019-10-17 Mehrdad Farajtabar , Navid Azizan , Alex Mott , Ang Li

In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data…

Machine Learning · Computer Science 2025-12-24 Minsu Kim , Seong-Hyeon Hwang , Steven Euijong Whang

The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks. Previously studied CL assumes that data are given in sequence nose-to-tail for different tasks, thus indeed belonging…

Machine Learning · Computer Science 2024-01-03 Fan Lyu , Wei Feng , Yuepan Li , Qing Sun , Fanhua Shang , Liang Wan , Liang Wang

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

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…

Computer Vision and Pattern Recognition · Computer Science 2020-10-19 Wei Chen , Yu Liu , Weiping Wang , Tinne Tuytelaars , Erwin M. Bakker , Michael Lew

Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary,…

Machine Learning · Computer Science 2024-10-17 Sihao Wu , Xingyu Zhao , Xiaowei Huang

Parameter-efficient fine-tuning (PEFT) has become a popular way to adapt large pre-trained models to new tasks. Most PEFT methods update only a small subset of parameters while freezing the rest, avoiding redundant computation. As they…

Machine Learning · Computer Science 2025-08-25 Sungmin Kang , Jisoo Kim , Salman Avestimehr , Sunwoo Lee

Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks, even with limited data records. Gradient-based…

Machine Learning · Computer Science 2026-04-16 Yilang Zhang , Abraham Jaeger Mountain , Bingcong Li , Georgios B. Giannakis

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

Machine Learning · Computer Science 2026-02-03 Hao Gu , Mao-Lin Luo , Zi-Hao Zhou , Han-Chen Zhang , Min-Ling Zhang , Tong Wei

Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic forgetting, where…

Computation and Language · Computer Science 2025-12-18 Xiaodi Li , Dingcheng Li , Rujun Gao , Mahmoud Zamani , Feng Mi , Latifur Khan

Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies in continuously updating foundation models to accommodate…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Wenxuan Zhang , Paul Janson , Rahaf Aljundi , Mohamed Elhoseiny

The recently introduced Gradient Methods with Memory use a subset of the past oracle information to create an accurate model of the objective function that enables them to surpass the Gradient Method in practical performance. The model…

Optimization and Control · Mathematics 2024-01-30 Mihai I. Florea

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Shixiang Tang , Dapeng Chen , Jinguo Zhu , Shijie Yu , Wanli Ouyang

Sequential learning in physical networks is hindered by catastrophic forgetting, where training a new task erases solutions to earlier ones. We show that we can significantly enhance memory of previous tasks by introducing a hard threshold…

Disordered Systems and Neural Networks · Physics 2025-12-04 Purba Chatterjee , Marcelo Guzman , Andrea J. Liu

Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Sanchar Palit , Biplab Banerjee , Subhasis Chaudhuri

For the goal of strong artificial intelligence that can mimic human-level intelligence, AI systems would have the ability to adapt to ever-changing scenarios and learn new knowledge continuously without forgetting previously acquired…

Quantum Physics · Physics 2025-11-18 Haozhen Situ , Tianxiang Lu , Minghua Pan , Lvzhou Li