Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Extendable and Iterative Structure Learning Strategy for Bayesian Networks

ICLR 2025 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an extendable, iterative structure learning strategy that adds a new variable to an existing Bayesian network without retraining from scratch.

Problem

Learning Bayesian network structure is computationally intensive and traditional algorithms must retrain from scratch when new variables are introduced, which is impractical for dynamic or large-scale settings.

Approach

Efficiently incorporates a new variable Y into an already-learned Bayesian network structure, avoiding full re-learning when variables are added.

Closest papers by meaning

• Learning Bayesian Networks in the Presence of Structural Side Information (AAAI 2022 · similarity 0.91)
• DiBS: Differentiable Bayesian Structure Learning (NeurIPS 2021 · similarity 0.91)
• Local-to-Global Bayesian Network Structure Learning (ICML 2017 · similarity 0.90)
• Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models (ICML 2018 · similarity 0.90)
• Efficient Bayesian Network Structure Learning via Parameterized Local Search on Topological Orderings (AAAI 2021 · similarity 0.90)
• Parallel Bayesian Network Structure Learning (ICML 2018 · similarity 0.90)