# MotifDisco: Motif Causal Discovery For Time Series Motifs

arXiv: https://arxiv.org/abs/2409.15219 · HTML: https://mlsanity.com/paper/2409.15219/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 22 of 22)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data](https://mlsanity.com/paper/2006.10833/) (2020)
- [Granger Causality: A Review and Recent Advances](https://mlsanity.com/paper/2105.02675/) (2021)
- [Causal Discovery from Temporal Data: An Overview and New Perspectives](https://mlsanity.com/paper/2303.10112/) (2023)
- [Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2201.04828/) (2022)
- [A Survey on Causal Discovery Methods for I.I.D. and Time Series Data](https://mlsanity.com/paper/2303.15027/) (2023)
- [TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery](https://mlsanity.com/paper/2310.19324/) (2023)
- [Disentangled Motif-aware Graph Learning for Phrase Grounding](https://mlsanity.com/paper/2104.06008/) (2021)
- [Motiflets -- Simple and Accurate Detection of Motifs in Time Series](https://mlsanity.com/paper/2206.03735/) (2022)
- [MotifExplainer: a Motif-based Graph Neural Network Explainer](https://mlsanity.com/paper/2202.00519/) (2022)
- [Multivariate Time Series Forecasting with Transfer Entropy Graph](https://mlsanity.com/paper/2005.01185/) (2020)
- [Motif Graph Neural Network](https://mlsanity.com/paper/2112.14900/) (2021)
- [Variable-lag Granger Causality and Transfer Entropy for Time Series Analysis](https://mlsanity.com/paper/2002.00208/) (2020)
- [Temporal Network Motifs: Models, Limitations, Evaluation](https://mlsanity.com/paper/2005.11817/) (2020)
- [Comprehensive Review and Empirical Evaluation of Causal Discovery Algorithms for Numerical Data](https://mlsanity.com/paper/2407.13054/) (2024)
- [Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection](https://mlsanity.com/paper/2108.06783/) (2021)
- [Entropy Causal Graphs for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2312.09478/) (2023)
- [Causal Feature Selection via Transfer Entropy](https://mlsanity.com/paper/2310.11059/) (2023)
- [Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.13251/) (2024)
- [GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces](https://mlsanity.com/paper/2303.01621/) (2023)
- [Framework for Variable-lag Motif Following Relation Inference In Time Series using Matrix Profile analysis](https://mlsanity.com/paper/2401.02860/) (2024)

## Abstract (arXiv)

Many time series, particularly health data streams, can be best understood as a sequence of phenomenon or events, which we call textitmotifs. A time series motif is a short trace segment which may implicitly capture an underlying phenomenon within the time series. Specifically, we focus on glucose traces collected from continuous glucose monitors (CGMs), which inherently contain motifs representing underlying human behaviors such as eating and exercise. The ability to identify and quantify textitcausal relationships amongst motifs can provide a mechanism to better understand and represent these patterns, useful for improving deep learning and generative models and for advanced technology development (e.g., personalized coaching and artificial insulin delivery systems). However, no previous work has developed causal discovery methods for time series motifs. Therefore, in this paper we develop MotifDisco (motif discovery of causality), a novel causal discovery framework to learn causal relations amongst motifs from time series traces. We formalize a notion of textitMotif Causality (MC), inspired from Granger Causality and Transfer Entropy, and develop a Graph Neural Network-based framework that learns causality between motifs by solving an unsupervised link prediction problem. We integrate MC with three model use cases of forecasting, anomaly detection and clustering, to showcase the use of MC as a building block for downstream tasks. Finally, we evaluate our framework on different health data streams and find that Motif Causality provides a significant performance improvement in all use cases.