Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913600331841536 |
|---|---|
| author | Chen, Haolin Garner, Philip N. |
| author_facet | Chen, Haolin Garner, Philip N. |
| contents | We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remains an issue with PEFT, damaging the pre-trained model's inherent capabilities. We demonstrate that existing Bayesian learning techniques can be applied to PEFT to prevent catastrophic forgetting as long as the parameter shift of the fine-tuned layers can be calculated differentiably. In a principled series of experiments on language modeling and speech synthesis tasks, we utilize established Laplace approximations, including diagonal and Kronecker-factored approaches, to regularize PEFT with the low-rank adaptation (LoRA) and compare their performance in pre-training knowledge preservation. Our results demonstrate that catastrophic forgetting can be overcome by our methods without degrading the fine-tuning performance, and using the Kronecker-factored approximation produces a better preservation of the pre-training knowledge than the diagonal ones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12220 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting Chen, Haolin Garner, Philip N. Audio and Speech Processing Machine Learning We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remains an issue with PEFT, damaging the pre-trained model's inherent capabilities. We demonstrate that existing Bayesian learning techniques can be applied to PEFT to prevent catastrophic forgetting as long as the parameter shift of the fine-tuned layers can be calculated differentiably. In a principled series of experiments on language modeling and speech synthesis tasks, we utilize established Laplace approximations, including diagonal and Kronecker-factored approaches, to regularize PEFT with the low-rank adaptation (LoRA) and compare their performance in pre-training knowledge preservation. Our results demonstrate that catastrophic forgetting can be overcome by our methods without degrading the fine-tuning performance, and using the Kronecker-factored approximation produces a better preservation of the pre-training knowledge than the diagonal ones. |
| title | Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting |
| topic | Audio and Speech Processing Machine Learning |
| url | https://arxiv.org/abs/2402.12220 |