mlsanityData to 14 Oct 2026

Asynchronous Graph Generator

arXiv 2309.17335 ↗First posted 29 Sep 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce the asynchronous graph generator (AGG), a novel graph attention network for imputation and prediction of multi-channel time series. Free from recurrent components or assumptions about temporal/spatial regularity, AGG encodes measurements, timestamps and channel-specific features directly in the nodes via learnable embeddings. Through an attention mechanism, these embeddings allow for discovering expressive relationships among the variables of interest in the form of a homogeneous graph. Once trained, AGG performs imputation by conditional attention generation, i.e., by creating a new node conditioned on given timestamps and channel specification. The proposed AGG is compared to related methods in the literature and its performance is analysed from a data augmentation perspective. Our experiments reveal that AGG achieved state-of-the-art results in time series imputation, classification and prediction for the benchmark datasets Beijing Air Quality, PhysioNet ICU 2012 and UCI localisation, outperforming other recent attention-based networks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

36 of 63 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2017Graph Attention Networkscited by 8,923
  6. 2016Layer Normalizationcited by 5,669
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  8. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  11. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  12. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
24 more
  1. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  2. 2021How Attentive are Graph Attention Networks?cited by 835
  3. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  4. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  5. 2015Gated Graph Sequence Neural Networkscited by 796
  6. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  7. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  8. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  9. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  10. 2014In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learningcited by 342
  11. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  12. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  13. 2015Diffusion-Convolutional Neural Networkscited by 268
  14. 2019Time2Vec: Learning a Vector Representation of Timecited by 213
  15. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 172
  16. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 165
  17. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 95
  18. 2017Implicit Regularization in Deep Learningcited by 90
  19. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  20. 2023Everything is Connected: Graph Neural Networkscited by 85
  21. 2016Modeling Missing Data in Clinical Time Series with RNNscited by 80
  22. 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 64
  23. 2019NAOMI: Non-Autoregressive Multiresolution Sequence Imputationcited by 59
  24. 2021Node Dependent Local Smoothing for Scalable Graph Learningcited by 45

Built on by

Not cited yet.