Data to 7 Oct 2026

Unsuitability of NOTEARS for Causal Graph Discovery

arXiv 2104.05441 ↗First posted 12 Apr 2021stat.ML cs.LG math.STcited by 46

Not on the map. Why?

Abstract (arXiv)

Causal Discovery methods aim to identify a DAG structure that represents causal relationships from observational data. In this article, we stress that it is important to test such methods for robustness in practical settings. As our main example, we analyze the NOTEARS method, for which we demonstrate a lack of scale-invariance. We show that NOTEARS is a method that aims to identify a parsimonious DAG from the data that explains the residual variance. We conclude that NOTEARS is not suitable for identifying truly causal relationships from the data.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

11 of 21 references.

References · 11

2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
2019Causality for Machine Learningcited by 242
2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
2019Learning Sparse Nonparametric DAGscited by 207
2020DYNOTEARS: Structure Learning from Time-Series Datacited by 198
2020On the Role of Sparsity and DAG Constraints for Learning Linear DAGscited by 186
2019Masked Gradient-Based Causal Structure Learningcited by 89
2013High-dimensional learning of linear causal networks via inverse covariance estimationcited by 86
2020Differentiable Causal Discovery Under Unmeasured Confoundingcited by 56
2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 16; 2024: 9; 2025: 4; 2026: 2.

46 papers.

Sort:

By area:

2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
2022Deep End-to-end Causal Inferencecited by 93
2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
2022Large-Scale Differentiable Causal Discovery of Factor Graphscited by 47
2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
2023Structure Learning with Continuous Optimization: A Sober Look and Beyondcited by 34
2023A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Modelscited by 28
2021FedDAG: Federated DAG Structure Learningcited by 17
2024Standardizing Structural Causal Modelscited by 17
2021Simultaneous Missing Value Imputation and Structure Learning with Groupscited by 16
2024Adjustment Identification Distance: A gadjid for Causal Structure Learningcited by 16
2022A Meta-Reinforcement Learning Algorithm for Causal Discoverycited by 11

34 more

2022CIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methodscited by 10
2023Constraint-Free Structure Learning with Smooth Acyclic Orientationscited by 10
2023Learning DAGs from Data with Few Root Causescited by 8
2023Causal Discovery from Time Series with Hybrids of Constraint-Based and Noise-Based Algorithmscited by 8
2024Comprehensive Review and Empirical Evaluation of Causal Discovery Algorithms for Numerical Datacited by 8
2023CDANs: Temporal Causal Discovery from Autocorrelated and Non-Stationary Time Series Datacited by 7
2023Open problems in causal structure learning: A case study of COVID-19 in the UKcited by 7
2023A Survey of Methods, Challenges and Perspectives in Causalitycited by 6
2024Better Simulations for Validating Causal Discovery with the DAG-Adaptation of the Onion Methodcited by 6
2024Large-Scale Targeted Cause Discovery via Learning from Simulated Datacited by 5
2022Tearing Apart NOTEARS: Controlling the Graph Prediction via Variance Manipulationcited by 4
2023Discovering Dynamic Causal Space for DAG Structure Learningcited by 4
2023Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choicecited by 4
2025CausalMan: A physics-based simulator for large-scale causalitycited by 4
2025Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarkscited by 4
2022Invariant Structure Learning for Better Generalization and Causal Explainabilitycited by 3
2023dotears: Scalable, consistent DAG estimation using observational and interventional datacited by 3
2022Trying to Outrun Causality with Machine Learning: Limitations of Model Explainability Techniques for Identifying Predictive Variablescited by 2
2022A Causal Research Pipeline and Tutorial for Psychologists and Social Scientistscited by 2
2021Application of quantum computing to a linear non-Gaussian acyclic model for novel medical knowledge discoverycited by 1
2023eCDANs: Efficient Temporal Causal Discovery from Autocorrelated and Non-stationary Data (Student Abstract)cited by 1
2023Relation-First Modeling Paradigm for Causal Representation Learning toward the Development of AGIcited by 1
2024Revisiting Differentiable Structure Learning: Inconsistency of ℓ1 Penalty and Beyondcited by 1
2024CGLearn: Consistent Gradient-Based Learning for Out-of-Distribution Generalizationcited by 1
2025Spectral structure learning for clinical time seriescited by 1
2025Heterogeneous Causal Discovery of Repeated Undesirable Health Outcomescited by 1
2022Inferring extended summary causal graphs from observational time seriescited by 0
2022Differentiable and Transportable Structure Learningcited by 0
2022DAPDAG: Domain Adaptation via Perturbed DAG Reconstructioncited by 0
2022Realization of Causal Representation Learning to Adjust Confounding Bias in Latent Spacecited by 0
2024Boosting Causal Additive Modelscited by 0
2024ExDBN: Learning Dynamic Bayesian Networks using Extended Mixed-Integer Programming Formulationscited by 0
2026Smoothing the Landscape: Causal Structure Learning via Diffusion Denoising Objectivescited by 0
2026PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discoverycited by 0