DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911426602336256 |
|---|---|
| author | Diep, Nghiem T. Dang, Hien Truong, Tuan Dinh, Tan Nguyen, Huy Ho, Nhat |
| author_facet | Diep, Nghiem T. Dang, Hien Truong, Tuan Dinh, Tan Nguyen, Huy Ho, Nhat |
| contents | Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the learning capacity and training stability of the Low-Rank Adaptation (LoRA) method by explicitly decomposing pre-trained weights into magnitude and directional components. In this work, we propose DoRAN, a new technique designed to stabilize training and boost the sample efficiency of DoRA. Our framework introduces two key components: (i) the injection of learnable noise into the denominator of DoRA weight decomposition, which serves as an adaptive regularizer to mitigate instabilities and improve the estimation rate of low-rank matrices; and (ii) the replacement of static low-rank matrices with auxiliary networks that generate them dynamically, enabling parameter coupling between the query and value projection matrices, leading to improved sample efficiency both theoretically and empirically. Comprehensive experiments on vision and language benchmarks show that DoRAN consistently outperforms LoRA, DoRA, and other PEFT baselines, underscoring the effectiveness of combining noise-based regularization with network-based parameter generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04331 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks Diep, Nghiem T. Dang, Hien Truong, Tuan Dinh, Tan Nguyen, Huy Ho, Nhat Machine Learning Computer Vision and Pattern Recognition Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the learning capacity and training stability of the Low-Rank Adaptation (LoRA) method by explicitly decomposing pre-trained weights into magnitude and directional components. In this work, we propose DoRAN, a new technique designed to stabilize training and boost the sample efficiency of DoRA. Our framework introduces two key components: (i) the injection of learnable noise into the denominator of DoRA weight decomposition, which serves as an adaptive regularizer to mitigate instabilities and improve the estimation rate of low-rank matrices; and (ii) the replacement of static low-rank matrices with auxiliary networks that generate them dynamically, enabling parameter coupling between the query and value projection matrices, leading to improved sample efficiency both theoretically and empirically. Comprehensive experiments on vision and language benchmarks show that DoRAN consistently outperforms LoRA, DoRA, and other PEFT baselines, underscoring the effectiveness of combining noise-based regularization with network-based parameter generation. |
| title | DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.04331 |