期限(时间)
系列(地层学)
状态空间
国家(计算机科学)
计算机科学
状态空间表示
时间序列
计量经济学
数学
算法
机器学习
物理
统计
地质学
古生物学
量子力学
作者
Xiuding Cai,Yaoyao Zhu,Xueyao Wang,Yu Yao
出处
期刊:Cornell University - arXiv
日期:2024-05-26
标识
DOI:10.48550/arxiv.2405.16440
摘要
In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state space models (SSMs), has emerged as a competitive alternative to Transformer, offering comparable performance with higher throughput and linear complexity related to sequence length. In this study, we analyze the limitations of current Mamba in LTSF and propose four targeted improvements, leading to MambaTS. We first introduce variable scan along time to arrange the historical information of all the variables together. We suggest that causal convolution in Mamba is not necessary for LTSF and propose the Temporal Mamba Block (TMB). We further incorporate a dropout mechanism for selective parameters of TMB to mitigate model overfitting. Moreover, we tackle the issue of variable scan order sensitivity by introducing variable permutation training. We further propose variable-aware scan along time to dynamically discover variable relationships during training and decode the optimal variable scan order by solving the shortest path visiting all nodes problem during inference. Extensive experiments conducted on eight public datasets demonstrate that MambaTS achieves new state-of-the-art performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI