mlsanityData to 14 Oct 2026

Long-term Forecasting using Higher Order Tensor RNNs

arXiv 1711.00073 ↗First posted 31 Oct 2017cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

We present Higher-Order Tensor RNN (HOT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics. Long-term forecasting in such systems is highly challenging, since there exist long-term temporal dependencies, higher-order correlations and sensitivity to error propagation. Our proposed recurrent architecture addresses these issues by learning the nonlinear dynamics directly using higher-order moments and higher-order state transition functions. Furthermore, we decompose the higher-order structure using the tensor-train decomposition to reduce the number of parameters while preserving the model performance. We theoretically establish the approximation guarantees and the variance bound for HOT-RNN for general sequence inputs. We also demonstrate 5% ~ 12% improvements for long-term prediction over general RNN and LSTM architectures on a range of simulated environments with nonlinear dynamics, as well on real-world time series data.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 10; 2023: 3; 2024: 4; 2025: 3; 2026: 2.

34 papers.

Sort:

  1. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  2. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  3. 2021Chaos as an interpretable benchmark for forecasting and data-driven modellingcited by 88
  4. 2021Granger Causality: A Review and Recent Advancescited by 63
  5. 2021Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Networkcited by 52
  6. 2021Network of Tensor Time Seriescited by 32
  7. 2021Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operatorscited by 29
  8. 2021QTN-VQC: An End-to-End Learning framework for Quantum Neural Networkscited by 27
  9. 2022FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecastingcited by 15
  10. 2022Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processingcited by 10
  11. 2021MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Datacited by 9
  12. 2021TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecastingcited by 8
22 more
  1. 2024Guaranteed Nonconvex Factorization Approach for Tensor Train Recoverycited by 8
  2. 2021Higher Order Recurrent Space-Time Transformer for Video Action Predictioncited by 6
  3. 2021Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecastingcited by 6
  4. 2025LETS Forecast: Learning Embedology for Time Series Forecastingcited by 6
  5. 2022Video Anomaly Detection via Prediction Network with Enhanced Spatio-Temporal Memory Exchangecited by 5
  6. 2025A Scalable Factorization Approach for High-Order Structured Tensor Recoverycited by 4
  7. 2022Towards Better Long-range Time Series Forecasting using Generative Forecastingcited by 3
  8. 2024WEITS: A Wavelet-enhanced residual framework for interpretable time series forecastingcited by 3
  9. 2022NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022cited by 2
  10. 2022Granger Causality using Neural Networkscited by 2
  11. 2023Hierarchical Joint Graph Learning and Multivariate Time Series Forecastingcited by 2
  12. 2023Boosting Defect Detection in Manufacturing using Tensor Convolutional Neural Networkscited by 2
  13. 2024Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformerscited by 2
  14. 2022Error Analysis of Tensor-Train Cross Approximationcited by 1
  15. 2022Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecastingcited by 1
  16. 2022Inductive Attention for Video Action Anticipationcited by 1
  17. 2024conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networkscited by 1
  18. 2021Towards Better Long-range Time Series Forecasting using Generative Adversarial Networkscited by 0
  19. 2023Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecturecited by 0
  20. 2025CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationaritycited by 0
  21. 2026FISformer: Replacing Self-Attention with a Fuzzy Inference System in Transformer Models for Time Series Forecastingcited by 0
  22. 2026Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecastingcited by 0