English
Related papers

Related papers: SLCA: Slow Learner with Classifier Alignment for C…

200 papers

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…

Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common…

Machine Learning · Computer Science 2020-03-04 Janice Lan , Rosanne Liu , Hattie Zhou , Jason Yosinski

Continual pre-training has increasingly become the predominant approach for adapting Large Language Models (LLMs) to new domains. This process involves updating the pre-trained LLM with a corpus from a new domain, resulting in a shift in…

Computation and Language · Computer Science 2024-06-28 Yiduo Guo , Jie Fu , Huishuai Zhang , Dongyan Zhao , Yikang Shen

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger…

Machine Learning · Computer Science 2025-02-20 Yifei Yang , Zouying Cao , Xinbei Ma , Yao Yao , Libo Qin , Zhi Chen , Hai Zhao

Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such…

Artificial Intelligence · Computer Science 2025-05-26 Jiachen Jiang , Jinxin Zhou , Zhihui Zhu

We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1)…

Machine Learning · Computer Science 2024-10-03 Kien X. Nguyen , Fengchun Qiao , Xi Peng

Continual learning requires learning incremental tasks with dynamic data distributions. So far, it has been observed that employing a combination of contrastive loss and distillation loss for training in continual learning yields strong…

Machine Learning · Computer Science 2024-05-30 Yichen Wen , Zhiquan Tan , Kaipeng Zheng , Chuanlong Xie , Weiran Huang

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…

Machine Learning · Statistics 2026-03-05 Korel Gundem , Juncheng Dong , Dennis Zhang , Vahid Tarokh , Zhengling Qi

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

In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information without forgetting old knowledge (i.e., Catastrophic…

The goal of continual learning (CL) is to learn different tasks over time. The main desiderata associated with CL are to maintain performance on older tasks, leverage the latter to improve learning of future tasks, and to introduce minimal…

Machine Learning · Computer Science 2022-06-22 Mustafa Burak Gurbuz , Constantine Dovrolis

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

Machine Learning · Computer Science 2023-09-04 Nicolas Michel , Giovanni Chierchia , Romain Negrel , Jean-François Bercher , Toshihiko Yamasaki

The Continual Learning (CL) problem involves performing well on a sequence of tasks under limited compute. Current algorithms in the domain are either slow, offline or sensitive to hyper-parameters. La-MAML, an optimization-based…

Machine Learning · Computer Science 2021-05-21 Joel Joseph , Alex Gu

Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adopted in continual…

Machine Learning · Computer Science 2025-09-01 Wei Li , Hangjie Yuan , Zixiang Zhao , Yifan Zhu , Aojun Lu , Tao Feng , Yanan Sun

Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive research has focused on CL within the context of…

Machine Learning · Computer Science 2024-06-10 Haotian Zhang , Junting Zhou , Haowei Lin , Hang Ye , Jianhua Zhu , Zihao Wang , Liangcai Gao , Yizhou Wang , Yitao Liang

The goal of Continual Learning (CL) task is to continuously learn multiple new tasks sequentially while achieving a balance between the plasticity and stability of new and old knowledge. This paper analyzes that this insufficiency arises…

Machine Learning · Computer Science 2024-05-28 Hanxi Xiao , Fan Lyu

Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. The models also need to be fine-tuned with specific instructions to maintain their ability to follow instructions…

Computation and Language · Computer Science 2024-10-15 Ishan Jindal , Chandana Badrinath , Pranjal Bharti , Lakkidi Vinay , Sachin Dev Sharma

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

Machine Learning · Computer Science 2021-01-29 Ghada Sokar , Decebal Constantin Mocanu , Mykola Pechenizkiy

The dilemma between plasticity and stability presents a significant challenge in Incremental Learning (IL), especially in the exemplar-free scenario where accessing old-task samples is strictly prohibited during the learning of a new task.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Wenju Sun , Qingyong Li , Wen Wang , Yangli-ao Geng
‹ Prev 1 4 5 6 7 8 10 Next ›