Dynamic Expert-Guided Model Averaging for Causal Discovery
Not on the map. Why?
Abstract (arXiv)
Would-be practitioners of causal discovery face a dizzying array of algorithms without a clear best choice. This abundance of competitive methods makes ensembling a natural strategy for practical applications. At the same time, real-world use cases frequently violate the assumptions on which common causal discovery algorithms are based, forcing reliance on expert knowledge. Inspired by recent work on dynamically requested expert knowledge and large language models (LLMs) as experts, we present a flexible model averaging method that integrates selective expert querying to ensemble a diverse set of causal discovery algorithms. Crucially, we distinguish between edge existence and orientation, enabling the method to leverage the complementary strengths of data-driven discovery and expert input. We further consider the realistic setting of limited access to an imperfect expert, using disagreement among algorithms to query the expert in cases of greater uncertainty. Experiments demonstrate that our method consistently outperforms strong baselines on both clean and noisy data. Code and data are available at https://anonymous.4open.science/r/expert-cd-ensemble-3282/.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 23 Jan 2026.
Builds on
23 of 37 references.
References · 23
- 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
- 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
- 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 166
- 2023Causal-learn: Causal Discovery in Pythoncited by 109
- 2021A survey of Bayesian Network structure learningcited by 87
- 2013Learning Equivalence Classes of Bayesian Networks Structurescited by 77
- 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 48
- 2023Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow-Shrink Treescited by 38
- 2021The impact of prior knowledge on causal structure learningcited by 35
- 2020Large-scale empirical validation of Bayesian Network structure learning algorithms with noisy datacited by 29
- 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
- 2023pgmpy: A Python Toolkit for Bayesian Networkscited by 23
11 more
- 2020A Comprehensive Scoping Review of Bayesian Networks in Healthcare: Past, Present and Futurecited by 22
- 2013Discovering Cyclic Causal Models with Latent Variables: A General SAT-Based Procedurecited by 18
- 2021Greedy structure learning from data that contain systematic missing valuescited by 13
- 2019Evaluating structure learning algorithms with a balanced scoring functioncited by 10
- 2023Py-Tetrad and RPy-Tetrad: A New Python Interface with R Support for Tetrad Causal Searchcited by 8
- 2021Effective and efficient structure learning with pruning and model averaging strategiescited by 7
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Recordscited by 6
- 2022The Impact of Variable Ordering on Bayesian Network Structure Learningcited by 5
- 2023Causal discovery using dynamically requested knowledgecited by 5
- 2024Investigating potential causes of Sepsis with Bayesian network structure learningcited by 4
- 2025Integrating Probabilistic Trees and Causal Networks for Clinical and Epidemiological Datacited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.