mlsanityData to 14 Oct 2026

Transparent Networks for Multivariate Time Series

arXiv 2410.10535 ↗First posted 14 Oct 2024cs.LG cs.CYcited by 2

Not on the map. Why?

Abstract (arXiv)

Transparent models, which provide inherently interpretable predictions, are receiving significant attention in high-stakes domains. However, despite much real-world data being collected as time series, there is a lack of studies on transparent time series models. To address this gap, we propose a novel transparent neural network model for time series called Generalized Additive Time Series Model (GATSM). GATSM consists of two parts: 1) independent feature networks to learn feature representations, and 2) a transparent temporal module to learn temporal patterns across different time steps using the feature representations. This structure allows GATSM to effectively capture temporal patterns and handle varying-length time series while preserving transparency. Empirical experiments show that GATSM significantly outperforms existing generalized additive models and achieves comparable performance to black-box time series models, such as recurrent neural networks and Transformer. In addition, we demonstrate that GATSM finds interesting patterns in time series.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 40 of its 67 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

40 of 67 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Graph Attention Networkscited by 8,923
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  6. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  8. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  9. 2018Neural Ordinary Differential Equationscited by 3,779
  10. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  11. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
28 more
  1. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  3. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  4. 2020Reformer: The Efficient Transformercited by 1,668
  5. 2020Rethinking Attention with Performerscited by 1,601
  6. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  10. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  11. 2018The UEA multivariate time series classification archive, 2018cited by 338
  12. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  13. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 246
  14. 2021NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learningcited by 88
  15. 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
  16. 2017Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillationcited by 62
  17. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  18. 2022Neural Basis Models for Interpretabilitycited by 56
  19. 2020How Interpretable and Trustworthy are GAMs?cited by 44
  20. 2018Stop Explaining Black Box Machine Learning Models for High Stakes Decisions and Use Interpretable Models Insteadcited by 40
  21. 2022Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selectioncited by 28
  22. 2022Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsitycited by 25
  23. 2022Scalable Interpretability via Polynomialscited by 25
  24. 2019A study of data and label shift in the LIME frameworkcited by 17
  25. 2021SurvNAM: The machine learning survival model explanationcited by 16
  26. 2022Treeformer: Dense Gradient Trees for Efficient Attention Computationcited by 9
  27. 2022Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactionscited by 7
  28. 2023The Blame Problem in Evaluating Local Explanations, and How to Tackle itcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregatecited by 0
  2. 2026Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learningcited by 0