Rehearsal-Free Modular and Compositional Continual Learning for Language Models
Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schuetze
Abstract
Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal-based, i.e., store data examples from previous tasks for data replay, or isolate parameters dedicated to each task. However, rehearsal-based methods raise privacy and memory issues, and parameter-isolation continual learning does not consider interaction between tasks, thus hindering knowledge transfer. In this work, we propose MoCL, a rehearsal-free **Mo**dular and **C**ompositional Continual **L**earning framework which continually adds new modules to language models and composes them with existing modules. Experiments on various benchmarks show that MoCL outperforms state of the art and effectively facilitates knowledge transfer.
BibTeX
@inproceedings{wang-etal-2024-rehearsal,
title = "Rehearsal-Free Modular and Compositional Continual Learning for Language Models",
author = {Wang, Mingyang and
Adel, Heike and
Lange, Lukas and
Str{\"o}tgen, Jannik and
Schuetze, Hinrich},
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.39/",
doi = "10.18653/v1/2024.naacl-short.39",
pages = "469--480"
}