Research map / Time series / Causal and generative time series
Causal Recurrent Variational Autoencoder for Medical Time Series Generation
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 CR-VAE instead of TCDF for causal discovery | Causal discovery models · Hénon, Lorenz-96, and fMRI | AUROC: 0.911 -> 0.960; 0.871 -> 0.954; 0.881 -> 0.957 | Helped |
| Use CR-VAE instead of VRAE | Time-series generation · Hénon | MMD: 0.125 -> 0.118 | Helped |
| Use CR-VAE instead of VRAE | Time-series generation · Lorenz-96 | MMD: 0.010 -> 0.015 | Hurt |
| Use CR-VAE instead of VRAE | Time-series generation · fMRI | TSTR RMSE: 0.119 -> 0.122 | Hurt |
| Use CR-VAE instead of VRAE | Time-series generation · EEG | TSTR RMSE: 0.030 -> 0.024 | Helped |
| Use past-only unidirectional encoder inputs instead of inputs that include future values (ablation) | CR-VAE causal discovery · Synthetic linear autoregressive process | Causal graph recovery | Helped |
| Add the error-compensation network (ablation) | CR-VAE generation · Synthetic linear autoregressive process | Generation quality | Helped |
| Add stage II training after sparsity-based training, fixing zero weights and continuing with SGD (ablation) | CR-VAE generation · fMRI | Generation quality | Helped |
Closest papers by meaning
- Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series (ICML 2025 · similarity 0.86)
- CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation (NeurIPS 2026 · similarity 0.85)
- Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference (ICML 2024 · similarity 0.85)
- Towards Identifiability of Hierarchical Temporal Causal Representation Learning (NeurIPS 2025 · similarity 0.85)
- A scalable generative model for dynamical system reconstruction from neuroimaging data (NeurIPS 2024 · similarity 0.85)
- Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder (ICLR 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.