Publikation
Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
Harsh Poonia; Felix Divo; Kristian Kersting; Devendra Singh Dhami
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2502.09981, Pages 1-24, Computing Research Repository, 2025.
Zusammenfassung
Causality in time series can be challenging to determine, especially in the presence
of non-linear dependencies. Granger causality helps analyze potential relation-
ships between variables, thereby offering a method to determine whether one
time series can predict—Granger cause—future values of another. Although suc-
cessful, 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 xL-
STMs (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 opti-
mization 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.