mlsanityData to 14 Oct 2026

FedDAG: Federated DAG Structure Learning

arXiv 2112.03555 ↗First posted 7 Dec 2021cs.LG stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server. However, due to the consideration of privacy protection, data owners gradually refuse to share their personalized raw data to avoid private information leakage, making this task more troublesome by cutting off the first step. Thus, a puzzle arises: textithow do we discover the underlying DAG structure from decentralized data? In this paper, focusing on the additive noise models (ANMs) assumption of data generation, we take the first step in developing a gradient-based learning framework named FedDAG, which can learn the DAG structure without directly touching the local data and also can naturally handle the data heterogeneity. Our method benefits from a two-level structure of each local model. The first level structure learns the edges and directions of the graph and communicates with the server to get the model information from other clients during the learning procedure, while the second level structure approximates the mechanisms among variables and personally updates on its own data to accommodate the data heterogeneity. Moreover, FedDAG formulates the overall learning task as a continuous optimization problem by taking advantage of an equality acyclicity constraint, which can be solved by gradient descent methods to boost the searching efficiency. Extensive experiments on both synthetic and real-world datasets verify the efficacy of the proposed method.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 42 of its 89 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

42 of 89 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2019Invariant Risk Minimizationcited by 1,854
  6. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  7. 2020Federated Learning with Matched Averagingcited by 564
  8. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  9. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  10. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  11. 2019Federated Machine Learning: Concept and Applicationscited by 412
  12. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
30 more
  1. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  2. 2019Gradient-Based Neural DAG Learningcited by 227
  3. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  4. 2019Learning Sparse Nonparametric DAGscited by 207
  5. 2020DYNOTEARS: Structure Learning from Time-Series Datacited by 200
  6. 2020On the Role of Sparsity and DAG Constraints for Learning Linear DAGscited by 191
  7. 2013CAM: Causal additive models, high-dimensional order search and penalized regressioncited by 178
  8. 2019Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changescited by 166
  9. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 153
  10. 2019Causal Discovery with Reinforcement Learningcited by 145
  11. 2021Federated Graph Classification over Non-IID Graphscited by 114
  12. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  13. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  14. 2019Masked Gradient-Based Causal Structure Learningcited by 89
  15. 2021A survey of Bayesian Network structure learningcited by 87
  16. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 85
  17. 2020DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networkscited by 66
  18. 2021gCastle: A Python Toolbox for Causal Discoverycited by 61
  19. 2020Differentiable Causal Discovery Under Unmeasured Confoundingcited by 56
  20. 2019A Graph Autoencoder Approach to Causal Structure Learningcited by 55
  21. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  22. 2021DAGs with No Curl: An Efficient DAG Structure Learning Approachcited by 53
  23. 2013Causal Discovery from Changescited by 52
  24. 2014Constraint-based Causal Discovery from Multiple Interventions over Overlapping Variable Setscited by 48
  25. 2021Unsuitability of NOTEARS for Causal Graph Discoverycited by 47
  26. 2021Learning Neural Causal Models with Active Interventionscited by 40
  27. 2020On the Convergence of Continuous Constrained Optimization for Structure Learningcited by 38
  28. 2020Domain Adaptation as a Problem of Inference on Graphical Modelscited by 36
  29. 2021Towards Federated Bayesian Network Structure Learning with Continuous Optimizationcited by 31
  30. 2020On Low Rank Directed Acyclic Graphs and Causal Structure Learningcited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 2; 2024: 5; 2025: 3; 2026: 3.

17 papers.

Sort:

  1. 2023Structure Learning with Continuous Optimization: A Sober Look and Beyondcited by 36
  2. 2024Federated Causal Discovery from Heterogeneous Datacited by 15
  3. 2022Distributed Learning of Generalized Linear Causal Networkscited by 13
  4. 2023MM-DAG: Multi-task DAG Learning for Multi-modal Data -- with Application for Traffic Congestion Analysiscited by 13
  5. 2022Towards Privacy-Aware Causal Structure Learning in Federated Settingcited by 11
  6. 2024psiDAG: Projected Stochastic Approximation Iteration for DAG Structure Learningcited by 4
  7. 2025The Robustness of Differentiable Causal Discovery in Misspecified Scenarioscited by 4
  8. 2022On the Sparse DAG Structure Learning Based on Adaptive Lassocited by 3
  9. 2025Regret-Based Federated Causal Discovery with Unknown Interventionscited by 2
  10. 2026Federated Causal Discovery Across Heterogeneous Datasets under Latent Confoundingcited by 2
  11. 2022Federated Causal Discovery From Interventionscited by 1
  12. 2024CCBNet: Confidential Collaborative Bayesian Networks Inferencecited by 1
5 more
  1. 2024Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guaranteescited by 1
  2. 2024Revisiting Differentiable Structure Learning: Inconsistency of ℓ1 Penalty and Beyondcited by 1
  3. 2025Differentially Private and Federated Structure Learning in Bayesian Networkscited by 1
  4. 2026Uncertainty Quantification in Federated Granger Causality Learningcited by 0
  5. 2026Beyond Weights and Gradients: A Taxonomy of Federated Learning Messagescited by 0