ss-Mamba: Semantic-Spline Selective State-Space Model
This work addresses time series forecasting for applications requiring efficiency and interpretability, offering an incremental improvement over existing methods.
The paper tackled time series forecasting by proposing ss-Mamba, a foundation model that integrates semantic-aware embeddings and spline-based temporal encoding within a selective state-space framework, achieving comparable performance to Transformers while reducing computational complexity from quadratic to linear time.
We propose ss-Mamba, a novel foundation model that enhances time series forecasting by integrating semantic-aware embeddings and adaptive spline-based temporal encoding within a selective state-space modeling framework. Building upon the recent success of Transformer architectures, ss-Mamba adopts the Mamba selective state space model as an efficient alternative that achieves comparable performance while significantly reducing computational complexity from quadratic to linear time. Semantic index embeddings, initialized from pretrained language models, allow effective generalization to previously unseen series through meaningful semantic priors. Additionally, spline-based Kolmogorov-Arnold Networks (KAN) dynamically and interpretably capture complex seasonalities and non-stationary temporal effects, providing a powerful enhancement over conventional temporal feature encodings. Extensive experimental evaluations confirm that ss-Mamba delivers superior accuracy, robustness, and interpretability, demonstrating its capability as a versatile and computationally efficient alternative to traditional Transformer-based models in time-series forecasting.