InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning

TL;DR

InfLoRA is a novel parameter-efficient fine-tuning method for continual learning that reparameterizes pre-trained weights to eliminate interference between tasks, balancing stability and plasticity effectively.

Contribution

This paper introduces InfLoRA, a new PEFT approach that reparameterizes weights to prevent task interference, improving continual learning performance.

Findings

Outperforms existing methods on multiple datasets

Balances stability and plasticity effectively

Reduces task interference in continual learning

Abstract

Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously (plasticity). Recently, parameter-efficient fine-tuning (PEFT), which involves freezing a pre-trained model and injecting a small number of learnable parameters to adapt to downstream tasks, has gained increasing popularity in continual learning. Although existing continual learning methods based on PEFT have demonstrated superior performance compared to those not based on PEFT, most of them do not consider how to eliminate the interference of the new task on the old tasks, which inhibits the model from making a good trade-off between stability and plasticity. In this work, we propose a new PEFT method, called interference-free low-rank adaptation (InfLoRA), for continual learning. InfLoRA injects a small number of parameters to reparameterize the pre-trained weights and shows that fine-tuning these injected parameters is equivalent to fine-tuning the pre-trained weights within a subspace. Furthermore, InfLoRA designs this subspace to eliminate the interference of the new task on the old tasks, making a good trade-off between stability and plasticity. Experimental results show that InfLoRA outperforms existing state-of-the-art continual learning methods on multiple datasets.