# Dynamic Expert-Guided Model Averaging for Causal Discovery

arXiv: https://arxiv.org/abs/2601.16715 · HTML: https://mlsanity.com/paper/2601.16715/

## 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 (most cited first, 23 of 23)

- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Causal Inference in the Presence of Latent Variables and Selection Bias](https://mlsanity.com/paper/1302.4983/) (2013)
- [Causal-learn: Causal Discovery in Python](https://mlsanity.com/paper/2307.16405/) (2023)
- [A survey of Bayesian Network structure learning](https://mlsanity.com/paper/2109.11415/) (2021)
- [Learning Equivalence Classes of Bayesian Networks Structures](https://mlsanity.com/paper/1302.3566/) (2013)
- [Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference](https://mlsanity.com/paper/2310.15117/) (2023)
- [Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow-Shrink Trees](https://mlsanity.com/paper/2310.17679/) (2023)
- [The impact of prior knowledge on causal structure learning](https://mlsanity.com/paper/2102.00473/) (2021)
- [Large-scale empirical validation of Bayesian Network structure learning algorithms with noisy data](https://mlsanity.com/paper/2005.09020/) (2020)
- [ALCM: Autonomous LLM-Augmented Causal Discovery Framework](https://mlsanity.com/paper/2405.01744/) (2024)
- [pgmpy: A Python Toolkit for Bayesian Networks](https://mlsanity.com/paper/2304.08639/) (2023)
- [A Comprehensive Scoping Review of Bayesian Networks in Healthcare: Past, Present and Future](https://mlsanity.com/paper/2002.08627/) (2020)
- [Discovering Cyclic Causal Models with Latent Variables: A General SAT-Based Procedure](https://mlsanity.com/paper/1309.6836/) (2013)
- [Greedy structure learning from data that contain systematic missing values](https://mlsanity.com/paper/2107.04184/) (2021)
- [Evaluating structure learning algorithms with a balanced scoring function](https://mlsanity.com/paper/1905.12666/) (2019)
- [Py-Tetrad and RPy-Tetrad: A New Python Interface with R Support for Tetrad Causal Search](https://mlsanity.com/paper/2308.07346/) (2023)
- [Effective and efficient structure learning with pruning and model averaging strategies](https://mlsanity.com/paper/2112.00398/) (2021)
- [SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records](https://mlsanity.com/paper/2409.08936/) (2024)
- [The Impact of Variable Ordering on Bayesian Network Structure Learning](https://mlsanity.com/paper/2206.08952/) (2022)
- [Causal discovery using dynamically requested knowledge](https://mlsanity.com/paper/2310.11154/) (2023)
- [Investigating potential causes of Sepsis with Bayesian network structure learning](https://mlsanity.com/paper/2406.09207/) (2024)
- [Integrating Probabilistic Trees and Causal Networks for Clinical and Epidemiological Data](https://mlsanity.com/paper/2501.15973/) (2025)

## Built on by (most cited first, 2 of 2)

- [PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning](https://mlsanity.com/paper/2605.07267/) (2026)
- [Stable Causal Discovery via Directed Acyclic Graph Aggregation](https://mlsanity.com/paper/2605.18633/) (2026)

## 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/.