Saved in:
Bibliographic Details
Main Authors: Wang, Mingyang, Adel, Heike, Lange, Lukas, Strötgen, Jannik, Schütze, Hinrich
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.18708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909232320741376
author Wang, Mingyang
Adel, Heike
Lange, Lukas
Strötgen, Jannik
Schütze, Hinrich
author_facet Wang, Mingyang
Adel, Heike
Lange, Lukas
Strötgen, Jannik
Schütze, Hinrich
contents In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned. While pretrained language models have shown impressive capabilities on various static tasks, applying them to continual learning poses significant challenges, including avoiding catastrophic forgetting, facilitating knowledge transfer, and maintaining parameter efficiency. In this paper, we introduce MoCL-P, a novel lightweight continual learning method that addresses these challenges simultaneously. Unlike traditional approaches that continuously expand parameters for newly arriving tasks, MoCL-P integrates task representation-guided module composition with adaptive pruning, effectively balancing knowledge integration and computational overhead. Our evaluation across three continual learning benchmarks with up to 176 tasks shows that MoCL-P achieves state-of-the-art performance and improves parameter efficiency by up to three times, demonstrating its potential for practical applications where resource requirements are constrained.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18708
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learn it or Leave it: Module Composition and Pruning for Continual Learning
Wang, Mingyang
Adel, Heike
Lange, Lukas
Strötgen, Jannik
Schütze, Hinrich
Machine Learning
Computation and Language
In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned. While pretrained language models have shown impressive capabilities on various static tasks, applying them to continual learning poses significant challenges, including avoiding catastrophic forgetting, facilitating knowledge transfer, and maintaining parameter efficiency. In this paper, we introduce MoCL-P, a novel lightweight continual learning method that addresses these challenges simultaneously. Unlike traditional approaches that continuously expand parameters for newly arriving tasks, MoCL-P integrates task representation-guided module composition with adaptive pruning, effectively balancing knowledge integration and computational overhead. Our evaluation across three continual learning benchmarks with up to 176 tasks shows that MoCL-P achieves state-of-the-art performance and improves parameter efficiency by up to three times, demonstrating its potential for practical applications where resource requirements are constrained.
title Learn it or Leave it: Module Composition and Pruning for Continual Learning
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2406.18708