Paper Review: HGTS‑Former – A Hierarchical Hypergraph Transformer for Multivariate Time‑Series Analysis

The HGTS‑Former model introduces a hierarchical hypergraph backbone combined with a Transformer to capture high‑order and dynamic dependencies in multivariate time‑series data, and experimental results on eight datasets show it consistently outperforms state‑of‑the‑art methods in both long‑term forecasting and interpolation tasks.

HGTS-FormerHypergraphTransformer

0 likes · 11 min read

Paper Review: HGTS‑Former – A Hierarchical Hypergraph Transformer for Multivariate Time‑Series Analysis

JD Tech Talk

Feb 24, 2021 · Artificial Intelligence

Memory-Gated Recurrent Networks for Multivariate Time Series Analysis

The paper introduces Memory-Gated Recurrent Networks (mGRN), a novel RNN architecture that separately captures marginal and joint memories of multivariate time series, demonstrating significant performance gains over LSTM/GRU across diverse applications such as ICU monitoring, speech recognition, handwriting, and high‑frequency stock price prediction.

AIRecurrent Neural Networkfinancial prediction

0 likes · 10 min read

Memory-Gated Recurrent Networks for Multivariate Time Series Analysis