State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
This addresses a bottleneck in fine-tuning SSMs for efficient adaptation, though it appears incremental as it adapts existing PEFT concepts to a specific model type.
The paper tackled the problem of applying Parameter-Efficient Fine-Tuning (PEFT) methods to State Space Models (SSMs), which are inefficient with prompt-based approaches, and introduced State-offset Tuning as a state-based method that directly adjusts state features, showing effectiveness across diverse datasets.
State Space Models (SSMs) have emerged as efficient alternatives to Transformers, mitigating their quadratic computational cost. However, the application of Parameter-Efficient Fine-Tuning (PEFT) methods to SSMs remains largely unexplored. In particular, prompt-based methods like Prompt Tuning and Prefix-Tuning, which are widely used in Transformers, do not perform well on SSMs. To address this, we propose state-based methods as a superior alternative to prompt-based methods. This new family of methods naturally stems from the architectural characteristics of SSMs. State-based methods adjust state-related features directly instead of depending on external prompts. Furthermore, we introduce a novel state-based PEFT method: State-offset Tuning. At every timestep, our method directly affects the state at the current step, leading to more effective adaptation. Through extensive experiments across diverse datasets, we demonstrate the effectiveness of our method. Code is available at https://github.com/furiosa-ai/ssm-state-tuning.