Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting (2401.00423v1)

Published 31 Dec 2023 in cs.LG

Abstract: Multivariate time series forecasting poses an ongoing challenge across various disciplines. Time series data often exhibit diverse intra-series and inter-series correlations, contributing to intricate and interwoven dependencies that have been the focus of numerous studies. Nevertheless, a significant research gap remains in comprehending the varying inter-series correlations across different time scales among multiple time series, an area that has received limited attention in the literature. To bridge this gap, this paper introduces MSGNet, an advanced deep learning model designed to capture the varying inter-series correlations across multiple time scales using frequency domain analysis and adaptive graph convolution. By leveraging frequency domain analysis, MSGNet effectively extracts salient periodic patterns and decomposes the time series into distinct time scales. The model incorporates a self-attention mechanism to capture intra-series dependencies, while introducing an adaptive mixhop graph convolution layer to autonomously learn diverse inter-series correlations within each time scale. Extensive experiments are conducted on several real-world datasets to showcase the effectiveness of MSGNet. Furthermore, MSGNet possesses the ability to automatically learn explainable multi-scale inter-series correlations, exhibiting strong generalization capabilities even when applied to out-of-distribution samples.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In ICML, 21–29. PMLR.
  2. Google COVID-19 community mobility reports: anonymization process description (version 1.1). arXiv preprint arXiv:2004.04145.
  3. Flights to safety. The Review of Financial Studies, 33(2): 689–746.
  4. Adaptive graph convolutional recurrent network for traffic forecasting. In Neurips, 33: 17804–17815.
  5. Accurate medium-range global weather forecasting with 3D neural networks. Nature, 1–6.
  6. Cao, L. 2022. Ai in finance: challenges, techniques, and opportunities. ACM Computing Surveys (CSUR), 55(3): 1–38.
  7. Towards understanding mixture of experts in deep learning. arXiv preprint arXiv:2208.02813.
  8. Scalable spatiotemporal graph neural networks. In AAAI, volume 37, 7218–7226.
  9. Long-term Forecasting with TiDE: Time-series Dense Encoder. arXiv preprint arXiv:2304.08424.
  10. Convolutional neural networks on graphs with fast localized spectral filtering. In Neurips, 29.
  11. DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting. In ICLR.
  12. Probabilistic forecasting with spline quantile function RNNs. In ICML, 1901–1910. PMLR.
  13. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Transactions on Knowledge and Data Engineering, 34(11): 5415–5428.
  14. Deep residual learning for image recognition. In CVPR, 770–778.
  15. Adaptive mixtures of local experts. Neural computation, 3(1): 79–87.
  16. Structural vector autoregressive analysis. Cambridge University Press.
  17. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  18. Semi-supervised classification with graph convolutional networks. In ICLR.
  19. Modeling long-and short-term temporal patterns with deep neural networks. In The 41st international ACM SIGIR conference on research & development in information retrieval, 95–104.
  20. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In ICLR.
  21. Non-stationary transformers: Exploring the stationarity in time series forecasting. In Neurips, 35: 9881–9893.
  22. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In ICLR.
  23. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. In ICLR.
  24. Deep state space models for time series forecasting. In Neurips, 31.
  25. DeepAR: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3): 1181–1191.
  26. Skeleton-based action recognition with directed graph neural networks. In CVPR, 7912–7921.
  27. Forecasting at scale. The American Statistician, 72(1): 37–45.
  28. Attention is all you need. In Neurips, 30.
  29. MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting. In ICLR.
  30. Transformers in time series: A survey. arXiv preprint arXiv:2202.07125.
  31. Scale and species richness: towards a general, hierarchical theory of species diversity. Journal of biogeography, 28(4): 453–470.
  32. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In ICLR.
  33. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In Neurips, 34: 22419–22430.
  34. Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction. IEEE Transactions on Knowledge and Data Engineering.
  35. Connecting the dots: Multivariate time series forecasting with graph neural networks. In KDD, 753–763.
  36. Graph wavenet for deep spatial-temporal graph modeling. In IJCAI, 1907–1913.
  37. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In IJCAI, 3634–3640.
  38. Ts2vec: Towards universal representation of time series. In AAAI, volume 36, 8980–8987.
  39. Are transformers effective for time series forecasting? In AAAI, volume 37, 11121–11128.
  40. Gman: A graph multi-attention network for traffic prediction. In AAAI, volume 34, 1234–1241.
  41. Informer: Beyond efficient transformer for long sequence time-series forecasting. In AAAI, volume 35, 11106–11115.
  42. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In ICML, 27268–27286. PMLR.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Wanlin Cai (3 papers)
  2. Yuxuan Liang (126 papers)
  3. Xianggen Liu (16 papers)
  4. Jianshuai Feng (1 paper)
  5. Yuankai Wu (29 papers)
Citations (33)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now