English
Related papers

Related papers: A Quantitative Characterization of Forgetting in P…

200 papers

Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than…

Machine Learning · Computer Science 2025-12-25 Weiwei Wang

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks),…

Machine Learning · Computer Science 2022-12-29 Jary Pomponi , Simone Scardapane , Aurelio Uncini

Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks). Due to the fact that past training data is not…

Machine Learning · Computer Science 2022-09-27 Qing Sun , Fan Lyu , Fanhua Shang , Wei Feng , Liang Wan

Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters. This work strives to reduce memory overhead in fine-tuning from perspectives of…

Machine Learning · Computer Science 2024-06-25 Yuchen Yang , Yingdong Shi , Cheems Wang , Xiantong Zhen , Yuxuan Shi , Jun Xu

We introduce a novel continual learning method based on multifidelity deep neural networks. This method learns the correlation between the output of previously trained models and the desired output of the model on the current training…

Numerical Analysis · Mathematics 2024-07-01 Amanda Howard , Yucheng Fu , Panos Stinis

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…

Computation and Language · Computer Science 2023-02-23 Sudipta Kar , Giuseppe Castellucci , Simone Filice , Shervin Malmasi , Oleg Rokhlenko

Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Dipam Goswami , Albin Soutif--Cormerais , Yuyang Liu , Sandesh Kamath , Bartłomiej Twardowski , Joost van de Weijer

Given the ease of creating synthetic data from machine learning models, new models can be potentially trained on synthetic data generated by previous models. This recursive training process raises concerns about the long-term impact on…

Machine Learning · Computer Science 2024-12-24 Ananda Theertha Suresh , Andrew Thangaraj , Aditya Nanda Kishore Khandavally

Learning new information without forgetting prior knowledge is central to human intelligence. In contrast, neural network models suffer from catastrophic forgetting: a significant degradation in performance on previously learned tasks when…

Machine Learning · Computer Science 2025-07-16 James P Jun , Vijay Marupudi , Raj Sanjay Shah , Sashank Varma

Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to meet continuously emerging requirements without expensive retraining. MCIT faces two major obstacles: catastrophic forgetting (where old…

Machine Learning · Computer Science 2024-06-28 Junhao Zheng , Qianli Ma , Zhen Liu , Binquan Wu , Huawen Feng

In this work, we propose three efficient restart paradigms for model-free non-stationary reinforcement learning (RL). We identify two core issues with the restart design of Mao et al. (2022)'s RestartQ-UCB algorithm: (1) complete…

Machine Learning · Computer Science 2025-10-15 Hiroshi Nonaka , Simon Ambrozak , Sofia R. Miskala-Dinc , Amedeo Ercole , Aviva Prins

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

As Large Language Models (LLMs) become increasingly computationally complex, developing efficient deployment strategies, such as quantization, becomes crucial. State-of-the-art Post-training Quantization (PTQ) techniques often rely on…

Machine Learning · Computer Science 2025-01-17 Alireza Ghaffari , Sharareh Younesian , Boxing Chen , Vahid Partovi Nia , Masoud Asgharian

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Rouzbeh Meshkinnejad , Jie Mei , Daniel Lizotte , Yalda Mohsenzadeh

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

Computation and Language · Computer Science 2025-11-07 Liran Cohen , Yaniv Nemcovesky , Avi Mendelson

Modern neural network based speech recognition models are required to continually absorb new data without re-training the whole system, especially in downstream applications using foundation models, having no access to the original training…

Computation and Language · Computer Science 2025-06-23 Enes Yavuz Ugan , Ngoc-Quan Pham , Alexander Waibel

This study delves into the intricate dynamics of trained deep neural networks and their relationships with network parameters. Trained networks predominantly continue training in a single direction, known as the drift mode. This drift mode…

Machine Learning · Computer Science 2023-11-02 David Haink

We present a modelling framework for the investigation of supervised learning in non-stationary environments. Specifically, we model two example types of learning systems: prototype-based Learning Vector Quantization (LVQ) for…

Machine Learning · Computer Science 2021-04-30 Michiel Straat , Fthi Abadi , Zhuoyun Kan , Christina Göpfert , Barbara Hammer , Michael Biehl

Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived from these dynamics include (i) the epoch at which examples…

Machine Learning · Computer Science 2022-10-28 Pratyush Maini , Saurabh Garg , Zachary C. Lipton , J. Zico Kolter

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or…

Machine Learning · Computer Science 2026-05-22 Dong Nie