Data to 7 Oct 2026

Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

arXiv 1912.09363 ↗First posted 19 Dec 2019stat.ML cs.LGcited by 748

Not on the map. Why?

Abstract (arXiv)

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target. While several deep learning models have been proposed for multi-step prediction, they typically comprise black-box models which do not account for the full range of inputs present in common scenarios. In this paper, we introduce the Temporal Fusion Transformer (TFT) -- a novel attention-based architecture which combines high-performance multi-horizon forecasting with interpretable insights into temporal dynamics. To learn temporal relationships at different scales, the TFT utilizes recurrent layers for local processing and interpretable self-attention layers for learning long-term dependencies. The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes. On a variety of real-world datasets, we demonstrate significant performance improvements over existing benchmarks, and showcase three practical interpretability use-cases of TFT.

Key facts. Cited by 748 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 43; 2022: 76; 2023: 119; 2024: 124; 2025: 180; 2026: 206.

748 papers.

Sort:

By area:

2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
2022Transformers in Time Series: A Surveycited by 489
2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 232
2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 188
2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 168
2025Chronos-2: From Univariate to Universal Forecastingcited by 158
2023TimeGPT-1cited by 149
2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116

38 more

2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 107
2023Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecastingcited by 102
2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
2021Darts: User-Friendly Modern Machine Learning for Time Seriescited by 90
2021Chaos as an interpretable benchmark for forecasting and data-driven modellingcited by 87
2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 86
2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 83
2023GIVT: Generative Infinite-Vocabulary Transformerscited by 80
2021Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Surveycited by 71
2022Sequential Predictive Conformal Inference for Time Seriescited by 71
2024TKAN: Temporal Kolmogorov-Arnold Networkscited by 70
2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 65
2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 63
2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
2023GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendationcited by 57
2023CARD: Channel Aligned Robust Blend Transformer for Time Series Forecastingcited by 55
2022Evaluation of post-hoc interpretability methods in time-series classificationcited by 53
2025fev-bench: A Realistic Benchmark for Time Series Forecastingcited by 52
2021GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environmentscited by 51
2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecastingcited by 50
2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 49
2021Long-Range Transformers for Dynamic Spatiotemporal Forecastingcited by 46
2021Do We Really Need Deep Learning Models for Time Series Forecasting?cited by 45
2022Transformers in Time-series Analysis: A Tutorialcited by 45
2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
2024MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selectioncited by 40
2024Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecastingcited by 40
2024Retrieval Augmented Time Series Forecastingcited by 40
2022TACTiS: Transformer-Attentional Copulas for Time Seriescited by 38
2024Conformal prediction for multi-dimensional time series by ellipsoidal setscited by 37
2023AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecastingcited by 36
2022A Comprehensive Survey of Regression Based Loss Functions for Time Series Forecastingcited by 33
2021Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecastingcited by 32
2022Deep Regression Unlearningcited by 32
2022High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learningcited by 31
2021Toward Explainable AI for Regression Modelscited by 30
2023How Does Attention Work in Vision Transformers? A Visual Analytics Attemptcited by 29

50 most cited of 748 All 748 (JSON)