LSEBMCL: A Latent Space Energy-Based Model for Continual Learning

TL;DR

This paper introduces LSEBMCL, a novel energy-based model that mitigates catastrophic forgetting in continual learning by sampling from previous tasks, demonstrating state-of-the-art results in NLP applications.

Contribution

It proposes using an energy-based model as an outer-generator to prevent forgetting, a new approach in continual learning for NLP tasks.

Findings

Achieves state-of-the-art results in NLP continual learning tasks.

Effectively prevents catastrophic forgetting using EBM sampling.

Demonstrates the efficacy of EBMs in practical NLP applications.

Abstract

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.