MambaTS framework offers improved time series forecasting without self-attention

Researchers have developed MambaTS, a new framework for long-term time series forecasting that utilizes a selective state space model as its backbone. Unlike traditional Transformers, MambaTS avoids the quadratic complexity of self-attention mechanisms. It introduces Variable-Aware Scan along Time (VAST) to learn inter-variable relationships and determine an optimal scan order. Experiments on eight datasets show MambaTS achieving competitive or state-of-the-art results. AI

IMPACT Offers a more efficient alternative to Transformers for long-term time series forecasting, potentially improving performance in applications relying on sequential data.

RANK_REASON The cluster contains an academic paper detailing a new model architecture for time series forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Mamba
• MambaTS
• Temporal Mamba Block
• Transformers
• Variable-Aware Scan along Time
• VAST
• Xiuding Cai

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →