Saved in:
Bibliographic Details
Main Authors: Li, Xiaodi, Li, Dingcheng, Gao, Rujun, Zamani, Mahmoud, Khan, Latifur
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.05495
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909453126729728
author Li, Xiaodi
Li, Dingcheng
Gao, Rujun
Zamani, Mahmoud
Khan, Latifur
author_facet Li, Xiaodi
Li, Dingcheng
Gao, Rujun
Zamani, Mahmoud
Khan, Latifur
contents Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards previously learned knowledge when it is trained on new tasks. Existing solutions involve storing exemplars from previous classes, regularizing parameters during the fine-tuning process, or assigning different model parameters to each task. The proposed solution LSEBMCL (Latent Space Energy-Based Model for Continual Learning) in this work is to use energy-based models (EBMs) to prevent catastrophic forgetting by sampling data points from previous tasks when training on new ones. The EBM is a machine learning model that associates an energy value with each input data point. The proposed method uses an EBM layer as an outer-generator in the continual learning framework for NLP tasks. The study demonstrates the efficacy of EBM in NLP tasks, achieving state-of-the-art results in all experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05495
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
Li, Xiaodi
Li, Dingcheng
Gao, Rujun
Zamani, Mahmoud
Khan, Latifur
Machine Learning
Artificial Intelligence
Computation and Language
Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards previously learned knowledge when it is trained on new tasks. Existing solutions involve storing exemplars from previous classes, regularizing parameters during the fine-tuning process, or assigning different model parameters to each task. The proposed solution LSEBMCL (Latent Space Energy-Based Model for Continual Learning) in this work is to use energy-based models (EBMs) to prevent catastrophic forgetting by sampling data points from previous tasks when training on new ones. The EBM is a machine learning model that associates an energy value with each input data point. The proposed method uses an EBM layer as an outer-generator in the continual learning framework for NLP tasks. The study demonstrates the efficacy of EBM in NLP tasks, achieving state-of-the-art results in all experiments.
title LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2501.05495