A data-free LoRA merging framework that decouples weight magnitude from direction and orthogonalizes directions to reduce task interference, outperforming existing merging methods across vision, language and multimodal models.
DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Low-rank adaptation (LoRA) reduces the computational and memory demands of fine-tuning large language models (LLMs) by approximating updates with low-rank matrices. However, low-rank approximation in two-dimensional space fails to capture high-dimensional structures within the target matrix. Recently, tensor decomposition methods have been explored for fine-tuning LLMs, leveraging their ability to extract structured information. Yet, these approaches primarily rely on random initialization, and the impact of initialization on tensor adaptation remains underexplored. In this paper, we reveal that random initialization significantly diverges from the validation loss achieved by full fine-tuning. To address this, we propose Weight-Decomposed Tensor Adaptation (DoTA), which leverages the Matrix Product Operator (MPO) decomposition of pre-trained weights for effective initialization in fine-tuning LLMs. Additionally, we introduce QDoTA, a quantized version of DoTA designed for 4-bit quantization. Experiments on commonsense and arithmetic reasoning tasks show that DoTA outperforms random initialization methods with fewer parameters. QDoTA further reduces memory consumption and achieves comparable performance to DoTA on commonsense reasoning tasks. We will release our code to support future research.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
A data-free LoRA merging framework that decouples weight magnitude from direction and orthogonalizes directions to reduce task interference, outperforming existing merging methods across vision, language and multimodal models.