paper-with-me

Papers

Few-Shot Regularization to Tackle Catastrophic Forgetting in Multilingual Machine Translation

2022-09-01 · AMTA 2022 9 · Salvador Carrión-Ponz None, Francisco Casacuberta

Increasing the number of tasks supported by a machine learning model without forgetting previously learned tasks is the goal of any lifelong learning system. In this work, we study how to mitigate the effects of the catastrophic forgetting problem to sequentially train a multilingual neural machine translation model using minimal past information. First, we describe the catastrophic forgetting phenomenon as a function of the number of tasks learned (language pairs) and the ratios of past data used during the learning of the new task. Next, we explore the importance of applying oversampling strategies for scenarios where only minimal amounts of past data are available. Finally, we derive a new loss function that minimizes the forgetting of previously learned tasks by actively re-weighting past samples and penalizing weights that deviate too much from the original model. Our work suggests that by using minimal amounts of past data and a simple regularization function, we can significantly mitigate the effects of the catastrophic forgetting phenomenon without increasing the computational costs.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learningMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Addressing Catastrophic Forgetting in Few-Shot Problems

2020-04-30 · Pauching Yap, Hippolyt Ritter, David Barber

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has bee…

ClassificationGeneral ClassificationMeta-LearningVariational Inference

Activity Regularization for Continual Learning

2019-05-01 · ICLR 2019 5 · Quang H. Pham, Steven C. H. Hoi

While deep neural networks have achieved remarkable successes, they suffer the well-known catastrophic forgetting issue when switching from existing tasks to tackle a new one. In this paper, we study continual learning w…

Continual LearningMulti-Task Learning

Incremental few-shot learning via vector quantization in deep embedded space

2021-01-01 · ICLR 2021 1 · Kuilin Chen, Chi-Guhn Lee

The capability of incrementally learning new tasks without forgetting old ones is a challenging problem due to catastrophic forgetting. This challenge becomes greater when novel tasks contain very few labelled training s…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningFew-Shot Learning+3

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models

2026-05-29 · Sanchit Ahuja, Terra Blevins arxiv

While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naïve finetuning on targeted data erodes existing capabilities through catastrophic forgetting. Organizing training a…

Reading ComprehensionContinual PretrainingLanguage AcquisitionGeneral Knowledge

Bayesian Online Meta-Learning

2020-09-28 · Pauching Yap, Hippolyt Ritter, David Barber

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem for large-scale supervised classification, little has be…

ClassificationMeta-LearningVariational Inference