Latent Space Factorization in LoRA
Shashi Kumar, Yacouba Kaloga, John Mtr., Petr Motlicek, Ina Kodrasi
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: https://github.com/idiap/FVAE-LoRA
BibTeX
@inproceedings{
kumar2025latent,
title={Latent Space Factorization in Lo{RA}},
author={Shashi Kumar and Yacouba Kaloga and John Mtr. and Petr Motlicek and Ina Kodrasi},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=Bqui2s3xFi}
}