Research map / Time series / Causal and generative time series
Graph-Guided Network for Irregularly Sampled Multivariate Time Series
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use sample-specific sensor dependency graphs and message passing (ablation) | Raindrop · P19, Setting 4: Train Male, Test Female | AUROC: 81.3 $\pm$ 1.5 -> 85.0 $\pm$ 1.4 | Helped |
| Add a binary missingness mask as input (ablation) | Raindrop · P19, Setting 1 | AUROC: +1.2% | Helped |
| Add a binary missingness mask as input (ablation) | Raindrop · P19, Setting 1 | AUPRC: +0.9% | Helped |
| Replace temporal attention with an LSTM (ablation) | Raindrop · P19, Setting 1 | AUROC: 1.8% | Hurt |
| Replace sensor concatenation with averaging (ablation) | Raindrop · P19, Setting 1 | AUROC: 0.6% | Hurt |
| Use Raindrop instead of DGM$^2$-O | irregular time-series classification · P19, Setting 1 | AUROC: 86.7 $\pm$ 3.4 -> 87.0 $\pm$ 2.3 | Helped |
| Use Raindrop instead of Transformer | irregular time-series classification · P19, Setting 1 | AUPRC: 47.6 $\pm$ 3.8 -> 51.8 $\pm$ 5.5 | Helped |
| Use Raindrop instead of IP-Net | irregular time-series classification · P12, Setting 1 | AUROC: 72.5 $\pm$ 2.4 -> 72.1 $\pm$ 1.3 | Hurt |
| Use Raindrop instead of DGM$^2$-O | irregular time-series classification · P12, Setting 1 | AUPRC: 96.9 $\pm$ 0.4 -> 97.0 $\pm$ 0.4 | Helped |
| Use Raindrop instead of Transformer | irregular time-series classification · PAM, Setting 1 | accuracy: 83.5 $\pm$ 1.5 -> 88.5 $\pm$ 1.5 | Helped |
| Use Raindrop instead of MTGNN | irregular time-series classification · PAM, Setting 1 | F1 score: 85.9 $\pm$ 2.4 -> 89.8 $\pm$ 1.0 | Helped |
Closest papers by meaning
- Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach (ICML 2024 · similarity 0.86)
- Motif-aware Graph Neural Networks for Networked Time Series Imputation (AAAI 2025 · similarity 0.86)
- Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series (NeurIPS 2024 · similarity 0.86)
- Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series (ICML 2025 · similarity 0.86)
- Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data (AAAI 2024 · similarity 0.85)
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.