AI Paper Atlas

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

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Differentiable and score-based DAG learning · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
use GFlowNet posterior instead of BCD-Nets with analytic linear solverl-DynBCD · synthetic linearBayes-SHD: 32.0 -> 22.8Improved
use GFlowNet posterior instead of DiBS with analytic linear solverl-DynDiBS · synthetic linearKL: 6622.43 -> 1091.60Improved
use h-DynGFN instead of h-DynBCDh-DynBCD · synthetic linearBayes-SHD: 5.5 -> 6.7No clear effect
use h-DynGFN instead of h-DynBCDh-DynBCD · synthetic linearKL: 701.19 -> 350.92Improved
use h-DynGFN instead of h-DynBCDh-DynBCD · synthetic non-linearBayes-SHD: 192.9 -> 32.6Improved
use l-DynGFN instead of l-DynBCDl-DynBCD · synthetic non-linearKL: 3814.86 -> 226.25Improved
use h-DynGFN instead of h-DynDiBSh-DynDiBS · synthetic non-linearKL: 8716.64 -> 193.28Improved
use l-DynGFN instead of l-DynBCDl-DynBCD · cellular RNA velocityKL: 321.95 -> 44.98Improved
use l-DynGFN instead of l-DynBCDl-DynBCD · cellular RNA velocityBayes-SHD: 2.6 -> 3.3Hurt
use h-DynGFN instead of h-DynDiBSh-DynDiBS · cellular RNA velocityNLL: 0.084 -> 0.109Hurt
increase sparsity from 0.90 to 0.95 (ablation)l-DynGFN · synthetic linear d=20Bayes-SHD: 22.8 -> 16.4Improved
decrease sparsity from 0.90 to 0.75 (ablation)l-DynGFN · synthetic linear d=20Bayes-SHD: 22.8 -> 60.2Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy