Latent Space Factorization in LoRA
| Type of publication: | Conference paper |
| Citation: | Kumar_NEURIPS2025_2025 |
| Publication status: | Accepted |
| Booktitle: | 39th Conference on Neural Information Processing Systems |
| Year: | 2025 |
| Month: | December |
| URL: | https://arxiv.org/abs/2510.196... |
| Abstract: | Low-rank adaptation (LoRA) is a widely used method for parameter-efficient finetuning. However, existing LoRA variants lack mechanisms to explicitly disambiguate task-relevant information within the learned low-rank subspace, potentially limiting downstream performance. We propose Factorized Variational Autoencoder LoRA (FVAE-LoRA), which leverages a VAE to learn two distinct latent spaces. Our novel Evidence Lower Bound formulation explicitly promotes factorization between the latent spaces, dedicating one latent space to task-salient features and the other to residual information. Extensive experiments on text, audio, and image tasks demonstrate that FVAE-LoRA consistently outperforms standard LoRA. Moreover, spurious correlation evaluations confirm that FVAE-LoRA better isolates task-relevant signals, leading to improved robustness under distribution shifts. Our code is publicly available at: \url{https://github.com/idiap/FVAE-LoRA} |
| Main Research Program: | Human-AI Teaming |
| Additional Research Programs: |
AI for Everyone |
| Keywords: | fvae-lora, latent space factorization, LoRA, low-rank adaptation, spurious correlation robustness |
| Projects: |
UNIPHORE ELOQUENCE ChaSpeePro |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
