mlsanityData to 7 Oct 2026

Tractable Uncertainty for Structure Learning

arXiv 2204.14170 ↗First posted 29 Apr 2022cs.LG cs.AI stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

Bayesian structure learning allows one to capture uncertainty over the causal directed acyclic graph (DAG) responsible for generating given data. In this work, we present Tractable Uncertainty for STructure learning (TRUST), a framework for approximate posterior inference that relies on probabilistic circuits as the representation of our posterior belief. In contrast to sample-based posterior approximations, our representation can capture a much richer space of DAGs, while also being able to tractably reason about the uncertainty through a range of useful inference queries. We empirically show how probabilistic circuits can be used as an augmented representation for structure learning methods, leading to improvement in both the quality of inferred structures and posterior uncertainty. Experimental results on conditional query answering further demonstrate the practical utility of the representational capacity of TRUST.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 14 of its 40 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

14 of 40 references.

References · 14

  1. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  2. 2021DiBS: Differentiable Bayesian Structure Learningcited by 105
  3. 2021BCD Nets: Scalable Variational Approaches for Bayesian Causal Discoverycited by 68
  4. 2019ABCD-Strategy: Budgeted Experimental Design for Targeted Causal Structure Discoverycited by 52
  5. 2021Variational Causal Networks: Approximate Bayesian Inference over Causal Structurescited by 43
  6. 2016On the Latent Variable Interpretation in Sum-Product Networkscited by 40
  7. 2015Partition MCMC for inference on acyclic digraphscited by 33
  8. 2020Towards Scalable Bayesian Learning of Causal DAGscited by 33
  9. 2014Addendum on the scoring of Gaussian directed acyclic graphical modelscited by 32
  10. 2018Efficient Sampling and Structure Learning of Bayesian Networkscited by 28
  11. 2020Probabilistic Circuits for Variational Inference in Discrete Graphical Modelscited by 20
  12. 2016Visualizing and Understanding Sum-Product Networkscited by 18
2 more
  1. 2017On Relaxing Determinism in Arithmetic Circuitscited by 14
  2. 2018Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

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

15 papers.

Sort:

  1. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  2. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  3. 2023Subtractive Mixture Models via Squaring: Representation and Learningcited by 39
  4. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  5. 2024A Compositional Atlas for Algebraic Circuitscited by 10
  6. 2025Scaling Probabilistic Circuits via Monarch Matricescited by 9
  7. 2023Characteristic Circuitscited by 8
  8. 2024Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challengescited by 8
  9. 2022Learning Latent Structural Causal Modelscited by 5
  10. 2024Permutation-based Inference for Variational Learning of Directed Acyclic Graphscited by 4
  11. 2024ProDAG: Projected Variational Inference for Directed Acyclic Graphscited by 4
  12. 2025Toward a Graph-Theoretic Model of Belief: Confidence, Credibility, and Structural Coherencecited by 1
3 more
  1. 2025Belief Graphs with Reasoning Zones: Structure, Dynamics, and Epistemic Activationcited by 1
  2. 2026SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discoverycited by 0
  3. 2026Interpretable Causal Discovery via Causal-Effect Constraintscited by 0