Parameter-Efficient Fine-Tuning of State Space Models
This addresses the need for efficient adaptation of SSM-based models, which are important for language modeling, but the approach is incremental as it builds on existing PEFT methods.
The paper tackles the problem of parameter-efficient fine-tuning for State Space Models (SSMs) like Mamba, finding that existing methods like LoRA underperform on SSM modules, and proposes Sparse Dimension Tuning (SDT) combined with LoRA to achieve state-of-the-art performance in experiments.
Deep State Space Models (SSMs), such as Mamba (Gu & Dao, 2024), have become powerful tools for language modeling, offering high performance and linear scalability with sequence length. However, the application of parameter-efficient fine-tuning (PEFT) methods to SSM-based models remains largely underexplored. We start by investigating two fundamental questions on existing PEFT methods: (i) How do they perform on SSM-based models? (ii) Which parameters should they target for optimal results? Our analysis shows that LoRA and its variants consistently outperform all other PEFT methods. While LoRA is effective for linear projection matrices, it fails on SSM modules-yet still outperforms other methods applicable to SSMs, indicating their limitations. This underscores the need for a specialized SSM tuning approach. To address this, we propose Sparse Dimension Tuning (SDT), a PEFT method tailored for SSM modules. Combining SDT for SSMs with LoRA for linear projection matrices, we achieve state-of-the-art performance across extensive experiments.