Summary of Emit- Event-based Masked Auto Encoding For Irregular Time Series, by Hrishikesh Patel et al.
EMIT- Event-Based Masked Auto Encoding for Irregular Time Series
by Hrishikesh Patel, Ruihong Qiu, Adam Irwin, Shazia Sadiq, Sen Wang
First submitted to arxiv on: 25 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 The proposed paper introduces a novel pretraining framework, EMIT, for irregular time series data in healthcare settings. This framework focuses on masking-based reconstruction in the latent space, selecting masking points based on the rate of change in the data. The approach preserves the natural variability and timing of measurements while enhancing the model’s ability to process irregular intervals without losing essential information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Irregular time series data is common in healthcare settings, like emergency wards where vital signs and lab results are recorded at varying times. This paper proposes a new way to train models for these types of data called EMIT (Event-Based Masking). It helps the model learn from the natural variability in the data and ignores parts that don’t matter. The approach performs well on two datasets, MIMIC-III and PhysioNet Challenge. |
Keywords
» Artificial intelligence » Latent space » Pretraining » Time series
