Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 54 references that are in the map. First posted on arXiv 14 Feb 2025.
Builds on
31 of 54 references.
References · 31
- 2017Attention Is All You Needcited by 60,361
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
- 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
- 2024KAN: Kolmogorov-Arnold Networkscited by 649
- 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
- 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
- 2024xLSTM: Extended Long Short-Term Memorycited by 327
- 2015LSTM: A Search Space Odysseycited by 316
- 2017Causal Consistency of Structural Equation Modelscited by 118
- 2024Is Mamba Effective for Time Series Forecasting?cited by 114
19 more
- 2020Benchmarking Deep Learning Interpretability in Time Series Predictionscited by 102
- 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 100
- 2016Learning Granger Causality for Hawkes Processescited by 69
- 2021Granger Causality: A Review and Recent Advancescited by 63
- 2019Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causalitycited by 55
- 2022Evaluation of post-hoc interpretability methods in time-series classificationcited by 53
- 2020Machine Learning Advances for Time Series Forecastingcited by 49
- 2021Interpretable Models for Granger Causality Using Self-explaining Neural Networkscited by 45
- 2023CUTS+: High-dimensional Causal Discovery from Irregular Time-seriescited by 41
- 2020CAUSE: Learning Granger Causality from Event Sequences using Attribution Methodscited by 36
- 2024xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memoriescited by 19
- 2020Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theorycited by 18
- 2024xLSTMTime : Long-term Time Series Forecasting With xLSTMcited by 14
- 2022Minimal Width for Universal Property of Deep RNNcited by 12
- 2015Granger Causality in Multi-variate Time Series using a Time Ordered Restricted Vector Autoregressive Modelcited by 8
- 2024Unveiling the Power of Sparse Neural Networks for Feature Selectioncited by 3
- 2024Forecasting Company Fundamentalscited by 3
- 2024Granger Causality Detection with Kolmogorov-Arnold Networkscited by 3
- 2021Non-Asymptotic Guarantees for Reliable Identification of Granger Causality via the LASSOcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.