用xLSTM增强因果分析，捕捉复杂数据中的长期依赖关系。
Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
- 引入动态损失惩罚，自动识别时间序列间的稀疏关联。
- 在六组数据上验证，能更稳定地恢复真实因果关系。
- 适合研究时间序列因果、长程依赖的学者与工程师。
时间序列中的因果关系难以确定，尤其在非线性依赖下。格兰杰因果分析可判断一个时间序列是否能预测另一个的未来值。然而现有方法仍难捕捉变量间的长程关系。为此，我们采用新兴的扩展长短期记忆网络（xLSTM）架构，提出格兰杰因果xLSTM（GC-xLSTM）。该模型通过新型动态损失惩罚，在初始投影阶段强制时间序列组件间的稀疏性，自适应优化并识别稀疏候选。联合优化过程确保了格兰杰因果关系的稳健恢复。在六组不同数据集上的实验验证了其有效性。
原文摘要 · Abstract (English)
Causality in time series can be challenging to determine, especially in the presence of non-linear dependencies. Granger causality helps analyze potential relationships between variables, thereby offering a method to determine whether one time series can predict-Granger cause-future values of another. Although successful, Granger causal methods still struggle with capturing long-range relations between variables. To this end, we leverage the recently successful Extended Long Short-Term Memory (xLSTM) architecture and propose Granger causal xLSTMs (GC-xLSTM). It first enforces sparsity between the time series components by using a novel dynamic loss penalty on the initial projection. Specifically, we adaptively improve the model and identify sparsity candidates. Our joint optimization procedure then ensures that the Granger causal relations are recovered robustly. Our experimental evaluation on six diverse datasets demonstrates the overall efficacy of GC-xLSTM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。