mlsanityData to 7 Oct 2026

GFlowCausal: Generative Flow Networks for Causal Discovery

arXiv 2210.08185 ↗First posted 15 Oct 2022cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Causal discovery aims to uncover causal structure among a set of variables. Score-based approaches mainly focus on searching for the best Directed Acyclic Graph (DAG) based on a predefined score function. However, most of them are not applicable on a large scale due to the limited searchability. Inspired by the active learning in generative flow networks, we propose a novel approach to learning a DAG from observational data called GFlowCausal. It converts the graph search problem to a generation problem, in which direct edges are added gradually. GFlowCausal aims to learn the best policy to generate high-reward DAGs by sequential actions with probabilities proportional to predefined rewards. We propose a plug-and-play module based on transitive closure to ensure efficient sampling. Theoretical analysis shows that this module could guarantee acyclicity properties effectively and the consistency between final states and fully-connected graphs. We conduct extensive experiments on both synthetic and real datasets, and results show the proposed approach to be superior and also performs well in a large-scale setting.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 15 Oct 2022.

Builds on

24 of 52 references.

References · 24

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  5. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  6. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
  7. 2013Causal Discovery with Continuous Additive Noise Modelscited by 252
  8. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  9. 2019Gradient-Based Neural DAG Learningcited by 227
  10. 2020On the Role of Sparsity and DAG Constraints for Learning Linear DAGscited by 186
  11. 2013Learning Bayesian Networks: The Combination of Knowledge and Statistical Datacited by 185
  12. 2013CAM: Causal additive models, high-dimensional order search and penalized regressioncited by 175
12 more
  1. 2022Biological Sequence Design with GFlowNetscited by 172
  2. 2021Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Gamecited by 159
  3. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  4. 2019Causal Discovery with Reinforcement Learningcited by 145
  5. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  6. 2020DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networkscited by 66
  7. 2013Learning Gaussian Networkscited by 62
  8. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  9. 2018Structural Agnostic Modeling: Adversarial Learning of Causal Graphscited by 48
  10. 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
  11. 2018A Constraint-Based Algorithm For Causal Discovery with Cycles, Latent Variables and Selection Biascited by 15
  12. 2020Causal Adversarial Network for Learning Conditional and Interventional Distributionscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 3; 2025: 1; 2026: 1.

11 papers.

  1. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  2. 2023Causal Deep Learningcited by 20
  3. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  4. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
  5. 2025Hybrid-Balance GFlowNet for Solving Vehicle Routing Problemscited by 7
  6. 2024CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learningcited by 6
  7. 2024Ada-HGNN: Adaptive Sampling for Scalable Hypergraph Neural Networkscited by 4
  8. 2023Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphscited by 3
  9. 2023GFlowNets with Human Feedbackcited by 3
  10. 2026Test-Time Learning of Causal Structure from Interventional Datacited by 2
  11. 2024Enhancing Solution Efficiency in Reinforcement Learning: Leveraging Sub-GFlowNet and Entropy Integrationcited by 0