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

Yan-Shuo Liang, Wu-Jun Li; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 23638-23647

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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_CVPR, author = {Liang, Yan-Shuo and Li, Wu-Jun}, title = {InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23638-23647} }