Unlocking Continual Learning Abilities in Language Models
Abstract: Language models (LMs) exhibit impressive performance and generalization capabilities.
However, LMs struggle with the persistent challenge of catastrophic forgetting, which undermines their long-term sustainability in continual learning (CL).
Existing approaches usually address the issue by incorporating old task data or task-wise inductive bias into LMs.
However, old data and accurate task information are often unavailable or costly to collect, hindering the availability of current CL approaches for LMs.
To address this limitation, we introduce ``MIGU''($\textbf{M}$agn$\textbf{I}$tude-based $\textbf{G}$radient $\textbf{U}$pdating for continual learning), a rehearsal-free and task-label-free method that only updates the model parameters with large magnitudes of output in LMs' linear layers.
MIGU is based on our observation that the normalized magnitude distribution of the output in LMs' linear layers is different when the LM models deal with different task data.
By imposing this simple constraint on the gradient update process, we can leverage the inherent behaviors of LMs, thereby unlocking their innate CL abilities.
Our experiments demonstrate that MIGU is universally applicable to all three LM architectures (T5, RoBERTa, and Llama2), delivering state-of-the-art or on-par performance across continual finetuning and continual pre-training settings on four CL benchmarks.
For example, MIGU brings a 15.2\% average accuracy improvement over conventional parameter-efficient finetuning baselines in a 15-task CL benchmark.
MIGU can also seamlessly integrate with all three existing CL types to further enhance performance.
We include the code in the submission attachment.
Paper Type: Long
Research Area: Machine Learning for NLP
Research Area Keywords: continual learning
Contribution Types: Model analysis & interpretability
Languages Studied: English
Submission Number: 3288
Loading