Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data

TL;DR

This paper introduces GC-xLSTM, a novel neural network architecture that enhances the detection of Granger causal relationships in complex, non-linear time series data by capturing long-range dependencies.

Contribution

It proposes a new method combining xLSTM with a dynamic loss penalty to enforce sparsity and improve causal inference in time series analysis.

Findings

Effective in identifying causal relations across diverse datasets

Outperforms existing methods in capturing long-range dependencies

Robustly recovers causal structures in complex data

Abstract

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.