English
Related papers

Related papers: Forget Me Not: Reducing Catastrophic Forgetting fo…

200 papers

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and…

Machine Learning · Computer Science 2026-03-17 Hang Thi-Thuy Le , Long Minh Bui , Minh Hoang , Trong Nghia Hoang

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

We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., words that provide a compact representation of the target…

Computation and Language · Computer Science 2023-07-17 Shahriar Golchin , Mihai Surdeanu , Nazgol Tavabi , Ata Kiapour

Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not…

Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We…

Computation and Language · Computer Science 2021-09-08 Haoran Xu , Seth Ebner , Mahsa Yarmohammadi , Aaron Steven White , Benjamin Van Durme , Kenton Murray

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…

Machine Learning · Computer Science 2026-03-31 Ali Taheri , Alireza Taban , Qizhou Wang , Shanshan Ye , Abdolreza Mirzaei , Tongliang Liu , Bo Han

We present META-MT, a meta-learning approach to adapt Neural Machine Translation (NMT) systems in a few-shot setting. META-MT provides a new approach to make NMT models easily adaptable to many target domains with the minimal amount of…

Computation and Language · Computer Science 2020-04-07 Amr Sharaf , Hany Hassan , Hal Daumé

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forgetting, which may harm…

Computation and Language · Computer Science 2024-02-09 Yongyu Yan , Kui Xue , Xiaoming Shi , Qi Ye , Jingping Liu , Tong Ruan

When a computational system continuously learns from an ever-changing environment, it rapidly forgets its past experiences. This phenomenon is called catastrophic forgetting. While a line of studies has been proposed with respect to…

Machine Learning · Statistics 2021-09-15 Haruka Asanuma , Shiro Takagi , Yoshihiro Nagano , Yuki Yoshida , Yasuhiko Igarashi , Masato Okada

This study tackles unsupervised domain adaptation of reading comprehension (UDARC). Reading comprehension (RC) is a task to learn the capability for question answering with textual sources. State-of-the-art models on RC still do not have…

Computation and Language · Computer Science 2020-05-22 Kosuke Nishida , Kyosuke Nishida , Itsumi Saito , Hisako Asano , Junji Tomita

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…

Computation and Language · Computer Science 2024-07-16 Jinhao Jiang , Junyi Li , Wayne Xin Zhao , Yang Song , Tao Zhang , Ji-Rong Wen

We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Ahmet Iscen , Thomas Bird , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Tobias Kalb , Björn Mauthe , Jürgen Beyerer

This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…

Computer Vision and Pattern Recognition · Computer Science 2023-09-11 Sandipan Choudhuri , Suli Adeniye , Arunabha Sen

Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to overfitting -- yet this is rarely seen in practice. But what…

Machine Learning · Computer Science 2025-07-14 Uri Stern , Eli Corn , Daphna Weinshall

Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP…

Machine Learning · Computer Science 2024-06-03 Stella Ho , Ming Liu , Shang Gao , Longxiang Gao

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Machine Learning · Computer Science 2019-11-27 David Rolnick , Arun Ahuja , Jonathan Schwarz , Timothy P. Lillicrap , Greg Wayne

Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are adapted to the target domain, e.g., fine-tuning, retraining.…

Sound · Computer Science 2019-04-18 Jiabin Xue , Jiqing Han , Tieran Zheng , Xiang Gao , Jiaxing Guo

In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…

Machine Learning · Computer Science 2019-11-28 Onur Tasar , Yuliya Tarabalka , Pierre Alliez

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known…

Computation and Language · Computer Science 2022-03-15 Qi Zhu , Bing Li , Fei Mi , Xiaoyan Zhu , Minlie Huang