Bayesian Structure Learning with Generative Flow Networks
By Tristan Deleu, Ant'onio G'ois, Chris C. Emezue, Mansi Rankawat, Simon Lacoste-Julien, Stefan Bauer, Yoshua Bengio. 2022
202 citations recorded by the source corpus.
In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian networks, from data. Defining such a distribution is very challenging, due to the combinatorially large sample space, and approximations based on MCMC are often required. Recently, a novel class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling of discrete and composite objects, such as graphs. In this work, we propose to use a GFlowNet as an alternative to MCMC for approximating the posterior distribution over the structure of Bayesian networks, given a dataset of observations. Generating a sample DAG from this approximate distribution is viewed as a sequential decision problem, where the graph is constructed one edge at a time, based on learned transition probabilities. Through evaluation on both simulated and real data, we show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs, and it compares favorably against other methods based on MCMC or variational inference.
Subfields: Artificial Intelligence, Probabilistic & Bayesian Methods
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Anirudh Goyal
- Yoshua Bengio
- Kyunghyun Cho
- Richard Socher
- Mohit Bansal
- Sergey Levine
- Aaron C. Courville
- Caiming Xiong
In Probabilistic & Bayesian Methods
- Anirudh Goyal
- Yoshua Bengio
- Pascal Vincent
- Aaron C. Courville
- Kyunghyun Cho
- Stefano Ermon
- L. Yao
- Asja Fischer
Citations in the corpus
- Inductive biases for deep learning of higher-level cognition (2020, background): “Causal structure learning is the recovery of the ground-truth C from observational and interventional data, possibly yielding a posterior distribution over causal structures compatible with the data, and a neural network can be trained to generate graphs from that posterior [235].”
- GFlowNet Foundations (2021, unknown): “Deleu et al. (2022) use a GFlowNet for structure learning; the GFlowNet produces samples that approximates the true posterior over causal graphs given a dataset.”