NeFut Logo NeFut
Admin Login

[CS.AI] SOS-LoRA: Static Orthogonal Subspace Low-Rank Adaptation

Published at: 2026-07-22 22:00 Last updated: 2026-07-23 12:33
#AI #Machine Learning #optimization

Abstract

Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models. Under a fixed rank budget, LoRA parameterizes each adapted weight through a single low-dimensional input-side pathway, which may couple heterogeneous behaviors through shared input directions and induce interference during optimization.

We propose Static Orthogonal Subspace LoRA (SOS-LoRA), a drop-in extension that reparameterizes a rank-rtot update as a sum of K static (always-on, non-routed) low-rank experts.

SOS-LoRA features:

  1. Decomposing the total rank across experts;
  2. Applying a fixed multi-scale scaling scheme to encourage scale-separated optimization dynamics;
  3. Promoting diverse input-side directions via cross-expert orthogonal initialization and a lightweight regularizer.

SOS-LoRA remains fully mergeable, adding no inference-time parameters or latency after merging. Experiments on reasoning and knowledge-intensive benchmarks (Llama 2/3), encoder-based NLU (GLUE), and math reasoning (GSM8K/MATH) show consistent gains over matched-budget LoRA baselines and recent variants. Code is available at GitHub.

Blogger's Review: SOS-LoRA enhances the flexibility and performance of low-rank adaptation by introducing static experts and multi-scale optimization, particularly excelling in complex reasoning tasks. This provides a fresh perspective for future model fine-tuning, warranting deeper exploration and application.

Original Source: https://arxiv.org/abs/2607.16252

[h] Back to Home