Summary of Motifdisco: Motif Causal Discovery For Time Series Motifs, by Josephine Lamp et al.
MotifDisco: Motif Causal Discovery For Time Series Motifs
by Josephine Lamp, Mark Derdzinski, Christopher Hannemann, Sam Hatfield, Joost van der Linden
First submitted to arxiv on: 23 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 Many health data streams can be understood as sequences of events or phenomena, known as motifs. In this paper, researchers focus on glucose traces from continuous glucose monitors (CGMs), which contain motifs representing human behaviors like eating and exercise. Identifying causal relationships amongst motifs can improve deep learning models and advanced technologies like personalized coaching and artificial insulin delivery systems. To address the lack of previous work on causal discovery methods for time series motifs, this paper develops MotifDisco, a novel framework that learns causal relations between motifs from time series traces using Graph Neural Networks and an unsupervised link prediction problem. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Motifs are short segments in time series data that can capture underlying patterns. This research focuses on glucose levels measured by continuous glucose monitors (CGMs). The goal is to understand these patterns better, which could help develop personalized coaching and artificial insulin delivery systems. To do this, the researchers developed a new way to discover causal relationships between these motifs. |
Keywords
» Artificial intelligence » Deep learning » Time series » Unsupervised
