# Memory-Gated Recurrent Networks

arXiv: https://arxiv.org/abs/2012.13121 · HTML: https://mlsanity.com/paper/2012.13121/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2020.

## Built on by (most cited first, 2 of 2)

- [CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification](https://mlsanity.com/paper/2203.04298/) (2022)
- [Probabilistic Learning of Multivariate Time Series with Temporal Irregularity](https://mlsanity.com/paper/2306.09147/) (2023)

## Abstract (arXiv)

The essence of multivariate sequential learning is all about how to extract dependencies in data. These data sets, such as hourly medical records in intensive care units and multi-frequency phonetic time series, often time exhibit not only strong serial dependencies in the individual components (the "marginal" memory) but also non-negligible memories in the cross-sectional dependencies (the "joint" memory). Because of the multivariate complexity in the evolution of the joint distribution that underlies the data generating process, we take a data-driven approach and construct a novel recurrent network architecture, termed Memory-Gated Recurrent Networks (mGRN), with gates explicitly regulating two distinct types of memories: the marginal memory and the joint memory. Through a combination of comprehensive simulation studies and empirical experiments on a range of public datasets, we show that our proposed mGRN architecture consistently outperforms state-of-the-art architectures targeting multivariate time series.