Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
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 |
|---|---|---|---|
| Increase the number of trajectories from D=5 to D=20 | Cluster variational CTBN · Synthetic CTBN, k_max=1 | AUROC: 0.78$\pm$ 0.03 -> 0.96$\pm$ 0.02 | Helped |
| Increase the number of trajectories from D=5 to D=20 | Cluster variational CTBN · Synthetic CTBN, k_max=1 | AUPR: 0.64$\pm$ 0.01 -> 0.92$\pm$ 0.00 | Helped |
| Increase measurement noise from σ=0.6 to σ=1.0 | Cluster variational CTBN · Synthetic CTBN, k_max=1 | AUROC: 0.81$\pm$ 0.10 -> 0.69$\pm$ 0.07 | Hurt |
| Increase measurement noise from σ=0.6 to σ=1.0 | Cluster variational CTBN · Synthetic CTBN, k_max=1 | AUPR: 0.71$\pm$ 0.00 -> 0.49$\pm$ 0.01 | Hurt |
| Increase the maximum parent count in the generated graphs from k_max=1 to k_max=2 | Cluster variational CTBN · Synthetic CTBN, D=10 | AUROC: 0.87$\pm$ 0.03 -> 0.68$\pm$ 0.12 | Hurt |
| Use the star approximation instead of the naive mean-field approximation (ablation) | CTBN variational inference · 8-node tree and undirected chain | MSE | Helped |
| Use the star approximation instead of the naive mean-field approximation (ablation) | CTBN variational inference · 8-node tree and undirected chain | Evidence approximation | Helped |
| Increase the maximum parent count in the generated graphs from k_max=1 to k_max=2 | Cluster variational CTBN · Synthetic CTBN, D=10 | AUPR: 0.76$\pm$ 0.00 -> 0.54$\pm$ 0.14 | Hurt |
Closest papers by meaning
- Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data (NeurIPS 2019 · similarity 0.94)
- Marginalized Continuous Time Bayesian Networks for Network Reconstruction from Incomplete Observations (AAAI 2016 · similarity 0.92)
- Active Learning of Continuous-time Bayesian Networks through Interventions (ICML 2021 · similarity 0.89)
- Continuous Time Bayesian Networks with Clocks (ICML 2020 · similarity 0.88)
- DiBS: Differentiable Bayesian Structure Learning (NeurIPS 2021 · similarity 0.88)
- Neural structure learning with stochastic differential equations (ICLR 2024 · similarity 0.87)
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.