mlsanityData to 14 Oct 2026

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

arXiv 2112.07459 ↗First posted 14 Dec 2021cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

26 of 50 references.

References · 26

  1. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  6. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  8. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  10. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  11. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  12. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
14 more
  1. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  2. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  3. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  4. 2017Progressive Neural Architecture Searchcited by 487
  5. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  6. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  7. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 157
  8. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  9. 2017Dilated Recurrent Neural Networkscited by 83
  10. 2019A Survey on Neural Architecture Searchcited by 71
  11. 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
  12. 2020FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecastingcited by 30
  13. 2018A Memory-Network Based Solution for Multivariate Time-Series Forecastingcited by 22
  14. 2020Multivariate Time Series Forecasting with Transfer Entropy Graphcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 4; 2025: 1; 2026: 1.

9 papers.

  1. 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecastingcited by 21
  2. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  3. 2023MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollerscited by 8
  4. 2023An algorithmic framework for the optimization of deep neural networks architectures and hyperparameterscited by 6
  5. 2024Automated Deep Learning for Load Forecastingcited by 3
  6. 2024Optimizing Time Series Forecasting Architectures: A Hierarchical Neural Architecture Search Approachcited by 3
  7. 2026Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysiscited by 2
  8. 2022An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Developmentcited by 0
  9. 2025Neural Architecture Search for global multi-step Forecasting of Energy Production Time Seriescited by 0