English
Related papers

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

200 papers

We introduce an approach for incremental learning that preserves feature descriptors of training images from previously learned classes, instead of the images themselves, unlike most existing work. Keeping the much lower-dimensional feature…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Ahmet Iscen , Jeffrey Zhang , Svetlana Lazebnik , Cordelia Schmid

Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottleneck. This paper challenges this paradigm by investigating…

Machine Learning · Computer Science 2026-02-19 Dongkyu Cho , Taesup Moon , Rumi Chunara , Kyunghyun Cho , Sungmin Cha

We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting in the absence of explicit task boundaries or identities. Among many efforts on task-free CL, a notable family of approaches are…

Machine Learning · Statistics 2021-12-09 Xisen Jin , Arka Sadhu , Junyi Du , Xiang Ren

Humans accumulate knowledge in a lifelong fashion. Modern deep neural networks, on the other hand, are susceptible to catastrophic forgetting: when adapted to perform new tasks, they often fail to preserve their performance on previously…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Mengyao Zhai , Lei Chen , Jiawei He , Megha Nawhal , Frederick Tung , Greg Mori

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Computation and Language · Computer Science 2025-10-20 Jessy Lin , Luke Zettlemoyer , Gargi Ghosh , Wen-Tau Yih , Aram Markosyan , Vincent-Pierre Berges , Barlas Oğuz

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Machine Learning · Computer Science 2018-11-16 Jing Shi , Jiaming Xu , Yiqun Yao , Bo Xu

One weakness of machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning (CL) paradigm has emerged as a protocol to systematically investigate…

Machine Learning · Computer Science 2022-03-02 Heinke Hihn , Daniel A. Braun

The ability to quickly learn new knowledge (e.g. new classes or data distributions) is a big step towards human-level intelligence. In this paper, we consider scenarios that require learning new classes or data distributions quickly and…

Machine Learning · Computer Science 2021-09-13 Fei Mi , Tao Lin , Boi Faltings

This paper aims for set-to-hypergraph prediction, where the goal is to infer the set of relations for a given set of entities. This is a common abstraction for applications in particle physics, biological systems, and combinatorial…

Machine Learning · Computer Science 2023-01-18 David W. Zhang , Gertjan J. Burghouts , Cees G. M. Snoek

Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint…

Machine Learning · Computer Science 2018-12-06 Jian Peng , Jiang Hao , Zhuo Li , Enqiang Guo , Xiaohong Wan , Deng Min , Qing Zhu , Haifeng Li

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…

Machine Learning · Computer Science 2022-08-18 Lin Ding , Peng Liu , Wenfeng Shen , Weijia Lu , Shengbo Chen

Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge. Existing gradient projection approaches impose hard constraints on the optimization space for new tasks to…

Machine Learning · Computer Science 2023-01-31 Zeyuan Yang , Zonghan Yang , Peng Li , Yang Liu

Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay -- by concurrently training externally…

We introduce Hindsight-Guided Momentum (HGM), a first-order optimization algorithm that adaptively scales learning rates based on the directional consistency of recent updates. Traditional adaptive methods, such as Adam or RMSprop , adapt…

Optimization and Control · Mathematics 2025-07-01 Krisanu Sarkar

Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types. One critical challenge is that the model would catastrophically forget old types…

Computation and Language · Computer Science 2022-09-19 Minqian Liu , Shiyu Chang , Lifu Huang

The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts…

Machine Learning · Computer Science 2019-07-08 Huaiyu Li , Weiming Dong , Bao-Gang Hu

The design of machines and algorithms capable of learning in a dynamically changing environment has become an increasingly topical problem with the increase of the size and heterogeneity of data available to learning systems. As a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Francesco Pelosin , Andrea Torsello

One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically…

Machine Learning · Computer Science 2022-11-16 Heinke Hihn , Daniel A. Braun

We investigate the properties of a recently proposed Gradient Echo Memory (GEM) scheme for information mapping between optical and atomic systems. We show that GEM can be described by the dynamic formation of polaritons in k-space. This…

Quantum Physics · Physics 2008-11-14 G. Hétet , J. J. Longdell , M. J. Sellars , P. K. Lam , B. C. Buchler

Recent advancements in Large Language Models (LLMs) have showcased their remarkable capabilities in text understanding and generation. However, even stronger LLMs are susceptible to acquiring erroneous or obsolete information from the…

Computation and Language · Computer Science 2024-02-19 Shiwen Ni , Dingwei Chen , Chengming Li , Xiping Hu , Ruifeng Xu , Min Yang
‹ Prev 1 3 4 5 6 7 10 Next ›