English
Related papers

Related papers: Grow, Don't Overwrite: Fine-tuning Without Forgett…

200 papers

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

Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models that are safe to deploy. Despite its clear importance, there…

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

Catastrophic forgetting is a significant challenge in continual learning, in which a model loses prior knowledge when it is fine-tuned on new tasks. This problem is particularly critical for large language models (LLMs) undergoing continual…

Computation and Language · Computer Science 2025-09-03 Ege Süalp , Mina Rezaei

Fine-tuning a pre-trained model on a downstream task often degrades its original capabilities, a phenomenon known as "catastrophic forgetting". This is especially an issue when one does not have access to the data and recipe used to develop…

Machine Learning · Computer Science 2025-06-13 Sunny Sanyal , Hayden Prairie , Rudrajit Das , Ali Kavis , Sujay Sanghavi

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 However, this knowledge becomes outdated or insufficient over time.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

Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a significant performance drop on the original tasks. This paper…

Computation and Language · Computer Science 2024-02-20 Didi Zhu , Zhongyi Sun , Zexi Li , Tao Shen , Ke Yan , Shouhong Ding , Kun Kuang , Chao Wu

Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An important step in making these pre-trained models effective…

Machine Learning · Computer Science 2024-07-02 Jishnu Mukhoti , Yarin Gal , Philip H. S. Torr , Puneet K. Dokania

Catastrophic forgetting remains a major challenge when adapting large language models (LLMs) to new tasks or domains. Conventional fine-tuning often overwrites existing knowledge, causing performance degradation on original tasks. We…

Computation and Language · Computer Science 2025-01-08 Ayoub Ben Chaliah , Hela Dellagi

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from that target domain. Finetuning presents two challenges: (i)…

Machine Learning · Computer Science 2025-05-28 Louis Bethune , David Grangier , Dan Busbridge , Eleonora Gualdoni , Marco Cuturi , Pierre Ablin

Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However,…

Computation and Language · Computer Science 2021-09-10 Haoming Jiang , Pengcheng He , Weizhu Chen , Xiaodong Liu , Jianfeng Gao , Tuo Zhao

Training state-of-the-art neural networks requires a high cost in terms of compute and time. Model scale is recognized to be a critical factor to achieve and improve the state-of-the-art. Increasing the scale of a neural network normally…

Machine Learning · Computer Science 2023-08-14 Andrea Gesmundo , Kaitlin Maile

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights…

Machine Learning · Computer Science 2019-10-31 Steven C. Y. Hung , Cheng-Hao Tu , Cheng-En Wu , Chien-Hung Chen , Yi-Ming Chan , Chu-Song Chen

Continual learning of new knowledge over time is one desirable capability for intelligent systems to recognize more and more classes of objects. Without or with very limited amount of old data stored, an intelligent system often…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Zhuoyun Li , Changhong Zhong , Sijia Liu , Ruixuan Wang , Wei-Shi Zheng

The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks. This issue is critical in practical supervised learning settings, such as the ones in…

Machine Learning · Computer Science 2023-06-09 Simone Marullo , Matteo Tiezzi , Marco Gori , Stefano Melacci , Tinne Tuytelaars

A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline,…

Machine Learning · Computer Science 2023-06-21 Rich Harang , Hillary Sanders

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Machine Learning · Computer Science 2020-12-16 Eden Belouadah , Adrian Popescu , Ioannis Kanellos

CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is the ability to transfer knowledge from a large source dataset…

Computer Vision and Pattern Recognition · Computer Science 2019-07-19 Yu-Xiong Wang , Deva Ramanan , Martial Hebert

Attention mechanisms have shown promising results in sequence modeling tasks that require long-term memory. Recent work investigated mechanisms to reduce the computational cost of preserving and storing memories. However, not all content in…

Machine Learning · Computer Science 2021-06-15 Sainbayar Sukhbaatar , Da Ju , Spencer Poff , Stephen Roller , Arthur Szlam , Jason Weston , Angela Fan
‹ Prev 1 2 3 10 Next ›