mlsanityData to 14 Oct 2026

Exploring Interpretable LSTM Neural Networks over Multi-Variable Data

arXiv 1905.12034 ↗First posted 28 May 2019cs.LG stat.MLcited by 42

Not on the map. Why?

Abstract (arXiv)

For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated training methods to jointly learn network parameters, variable and temporal importance w.r.t the prediction of the target variable. Extensive experiments on real datasets demonstrate enhanced prediction performance by capturing the dynamics of different variables. Meanwhile, we evaluate the interpretation results both qualitatively and quantitatively. It exhibits the prospect as an end-to-end framework for both forecasting and knowledge extraction over multi-variable data.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 7; 2024: 8; 2025: 5; 2026: 3.

42 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  2. 2021Explaining Time Series Predictions with Dynamic Maskscited by 73
  3. 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
  4. 2022WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Valuescited by 24
  5. 2021A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecastingcited by 21
  6. 2022Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformerscited by 18
  7. 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
  8. 2021SSDNet: State Space Decomposition Neural Network for Time Series Forecastingcited by 15
  9. 2021A Transfer Learning-based State of Charge Estimation for Lithium-Ion Battery at Varying Ambient Temperaturescited by 14
  10. 2024A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecastingcited by 14
  11. 2021Inductive Granger Causal Modeling for Multivariate Time Seriescited by 8
  12. 2022Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wildcited by 8
30 more
  1. 2021Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutionscited by 7
  2. 2023MTS2Graph: Interpretable Multivariate Time Series Classification with Temporal Evolving Graphscited by 7
  3. 2024Embracing the black box: Heading towards foundation models for causal discovery from time series datacited by 7
  4. 2024Deep Coupling Network For Multivariate Time Series Forecastingcited by 6
  5. 2021Mixture of Linear Models Co-supervised by Deep Neural Networkscited by 5
  6. 2022TreeDRNet:A Robust Deep Model for Long Term Time Series Forecastingcited by 4
  7. 2026Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemicscited by 4
  8. 2024Predicting machine failures from multivariate time series: an industrial case studycited by 3
  9. 2024WEITS: A Wavelet-enhanced residual framework for interpretable time series forecastingcited by 3
  10. 2021Modality Fusion Network and Personalized Attention in Momentary Stress Detection in the Wildcited by 2
  11. 2022NeuroView-RNN: It's About Timecited by 2
  12. 2022EgPDE-Net: Building Continuous Neural Networks for Time Series Prediction with Exogenous Variablescited by 2
  13. 2023FV-MgNet: Fully Connected V-cycle MgNet for Interpretable Time Series Forecastingcited by 2
  14. 2024GARNN: An Interpretable Graph Attentive Recurrent Neural Network for Predicting Blood Glucose Levels via Multivariate Time Seriescited by 2
  15. 2021Interpretable Additive Recurrent Neural Networks For Multivariate Clinical Time Seriescited by 1
  16. 2022The Right Tool for the Job: Open-Source Auditing Tools in Machine Learningcited by 1
  17. 2023DANLIP: Deep Autoregressive Networks for Locally Interpretable Probabilistic Forecastingcited by 1
  18. 2023Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecastingcited by 1
  19. 2025Understanding Mental Health Content on Social Media and Its Effect Towards Suicidal Ideationcited by 1
  20. 2025Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysiscited by 1
  21. 2022Automated dysgraphia detection by deep learning with SensoGripcited by 0
  22. 2023Distributed LSTM-Learning from Differentially Private Label Proportionscited by 0
  23. 2023DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Seriescited by 0
  24. 2024Machine-Learned Closure of URANS for Stably Stratified Turbulence: Connecting Physical Timescales & Data Hyperparameters of Deep Time-Series Modelscited by 0
  25. 2024Distributed Lag Transformer based on Time-Variable-Aware Learning for Explainable Multivariate Time Series Forecastingcited by 0
  26. 2025Interpretable deep convolutional model for nonlinear multivariate time series in complex systemscited by 0
  27. 2025Learning Temporal Saliency for Time Series Forecasting with Cross-Scale Attentioncited by 0
  28. 2025A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecastingcited by 0
  29. 2026Development of Vision-Language Model-based GNSS Spoofing Detection for Autonomous Vehicle Navigationcited by 0
  30. 2026GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Carecited by 0