mlsanityData to 7 Oct 2026

Multi-Source Knowledge-Based Hybrid Neural Framework for Time Series Representation Learning

arXiv 2408.12409 ↗First posted 22 Aug 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurately predicting the behavior of complex dynamical systems, characterized by high-dimensional multivariate time series(MTS) in interconnected sensor networks, is crucial for informed decision-making in various applications to minimize risk. While graph forecasting networks(GFNs) are ideal for forecasting MTS data that exhibit spatio-temporal dependencies, prior works rely solely on the domain-specific knowledge of time-series variables inter-relationships to model the nonlinear dynamics, neglecting inherent relational structural dependencies among the variables within the MTS data. In contrast, contemporary works infer relational structures from MTS data but neglect domain-specific knowledge. The proposed hybrid architecture addresses these limitations by combining both domain-specific knowledge and implicit knowledge of the relational structure underlying the MTS data using Knowledge-Based Compositional Generalization. The hybrid architecture shows promising results on multiple benchmark datasets, outperforming state-of-the-art forecasting methods. Additionally, the architecture models the time varying uncertainty of multi-horizon forecasts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 59 references that are in the map. First posted on arXiv 22 Aug 2024.

Builds on

31 of 59 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2016Layer Normalizationcited by 5,579
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  9. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  10. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  11. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  12. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
19 more
  1. 2016Language Modeling with Gated Convolutional Networkscited by 688
  2. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  3. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  4. 2019Graph U-Netscited by 489
  5. 2019Self-Attention Graph Poolingcited by 421
  6. 2018Neural Relational Inference for Interacting Systemscited by 339
  7. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  8. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  9. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 209
  10. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 169
  11. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  12. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  13. 2021DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Predictioncited by 73
  14. 2021Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecastingcited by 67
  15. 2019STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecastingcited by 59
  16. 2017Graph Classification via Deep Learning with Virtual Nodescited by 30
  17. 2019Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networkscited by 20
  18. 2021Hierarchical graph neural nets can capture long-range interactionscited by 12
  19. 2019Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysiscited by 10

Built on by

Not cited yet.