Summary of Uncertainty-aware Deep Attention Recurrent Neural Network For Heterogeneous Time Series Imputation, by Linglong Qian et al.
Uncertainty-Aware Deep Attention Recurrent Neural Network for Heterogeneous Time Series Imputation
by Linglong Qian, Zina Ibrahim, Richard Dobson
First submitted to arxiv on: 4 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a deep recurrent neural network called DEep Attention Recurrent Imputation (DEARI) for jointly estimating missing values and their associated uncertainty in multivariate time series. The model uses a self-attention mechanism to represent feature-wise correlations and temporal dynamics, along with an effective residual component, to achieve good imputation performance and stable convergence. Additionally, the authors leverage self-supervised metric learning to optimize sample similarity and transform DEARI into a Bayesian neural network through a novel Bayesian marginalization strategy, resulting in stochastic DEARI that outperforms its deterministic equivalent. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps solve a big problem with missing data in complex datasets. Right now, we don’t have a good way to fill in the gaps and also know how sure we are of our answers. The new model, called DEARI, does both at the same time! It looks at patterns in the data and uses those patterns to make predictions about what’s missing. This helps us get more accurate results and reduces bias. The authors tested DEARI on real-world datasets from different fields like air quality control, healthcare, and traffic, and it outperformed the current best method. |
Keywords
* Artificial intelligence * Attention * Neural network * Self attention * Self supervised * Time series
