Sökning: onr:"swepub:oai:DiVA.org:kth-327050" >
Bayesian Structure ...
Bayesian Structure Learning with Generative Flow Networks
-
- Deleu, T. (författare)
- Mila, Université de Montréal, Mila, Université de Montréal.
-
- Góis, A. (författare)
- Mila, Université de Montréal, Mila, Université de Montréal.
-
- Emezue, C. (författare)
- Technical University of Munich, Technical University of Munich
-
visa fler...
-
- Rankawat, M. (författare)
- Mila, Université de Montréal, Mila, Université de Montréal
-
- Lacoste-Julien, S. (författare)
- Mila, Université de Montréal, Mila, Université de Montréal; CIFAR AI, CIFAR AI
-
- Bauer, Stefan (författare)
- KTH,Intelligenta system,CIFAR Azrieli Global, Canada
-
- Bengio, Y. (författare)
- Mila, Université de Montréal, Mila, Université de Montréal; CIFAR AI, CIFAR AI; CIFAR, CIFAR
-
visa färre...
-
Mila, Université de Montréal, Mila, Université de Montréal Technical University of Munich, Technical University of Munich (creator_code:org_t)
- Association For Uncertainty in Artificial Intelligence (AUAI), 2022
- 2022
- Engelska.
-
Ingår i: Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022. - : Association For Uncertainty in Artificial Intelligence (AUAI). ; , s. 518-528
- Relaterad länk:
-
https://urn.kb.se/re...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Artificial intelligence
- Flow graphs
- Probability distributions
- Acyclic graphs
- Bayesia n networks
- Bayesian structure learning
- Composite objects
- Discrete objects
- Flow network
- Generative model
- Graph structures
- Probabilistic models
- Sample space
- Bayesian networks
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)