Research map / Probabilistic and scientific modeling / Causal discovery
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
Lazar Atanackovic, Alexander Tong, BO WANG, Leo J Lee, Yoshua Bengio, Jason Hartford
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 GFlowNet posterior instead of BCD-Nets with analytic linear solver | l-DynBCD · synthetic linear | Bayes-SHD: 32.0 -> 22.8 | Improved |
| use GFlowNet posterior instead of DiBS with analytic linear solver | l-DynDiBS · synthetic linear | KL: 6622.43 -> 1091.60 | Improved |
| use h-DynGFN instead of h-DynBCD | h-DynBCD · synthetic linear | Bayes-SHD: 5.5 -> 6.7 | No clear effect |
| use h-DynGFN instead of h-DynBCD | h-DynBCD · synthetic linear | KL: 701.19 -> 350.92 | Improved |
| use h-DynGFN instead of h-DynBCD | h-DynBCD · synthetic non-linear | Bayes-SHD: 192.9 -> 32.6 | Improved |
| use l-DynGFN instead of l-DynBCD | l-DynBCD · synthetic non-linear | KL: 3814.86 -> 226.25 | Improved |
| use h-DynGFN instead of h-DynDiBS | h-DynDiBS · synthetic non-linear | KL: 8716.64 -> 193.28 | Improved |
| use l-DynGFN instead of l-DynBCD | l-DynBCD · cellular RNA velocity | KL: 321.95 -> 44.98 | Improved |
| use l-DynGFN instead of l-DynBCD | l-DynBCD · cellular RNA velocity | Bayes-SHD: 2.6 -> 3.3 | Hurt |
| use h-DynGFN instead of h-DynDiBS | h-DynDiBS · cellular RNA velocity | NLL: 0.084 -> 0.109 | Hurt |
| increase sparsity from 0.90 to 0.95 (ablation) | l-DynGFN · synthetic linear d=20 | Bayes-SHD: 22.8 -> 16.4 | Improved |
| decrease sparsity from 0.90 to 0.75 (ablation) | l-DynGFN · synthetic linear d=20 | Bayes-SHD: 22.8 -> 60.2 | Hurt |
Closest papers by meaning
- KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference (NeurIPS 2025 · similarity 0.88)
- Deep Gaussian Processes on Directed Acyclic Graphs (NeurIPS 2026 · similarity 0.86)
- Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders (NeurIPS 2025 · similarity 0.86)
- Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View (ICLR 2024 · similarity 0.86)
- Pruning neural network models for gene regulatory dynamics using data and domain knowledge (NeurIPS 2024 · similarity 0.85)
- gfnx: Fast and Scalable Library for Generative Flow Networks in JAX (NeurIPS 2026 · 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.
