DiBS: Differentiable Bayesian Structure Learning
This work addresses the need for efficient and general posterior inference in Bayesian networks, which is crucial for active causal discovery and intervention design in real-world systems, representing a novel method for a known bottleneck.
The authors tackled the problem of Bayesian structure learning for inferring Bayesian network structures with uncertainty, proposing DiBS, a differentiable framework that jointly infers graph structures and parameters, and it significantly outperformed related methods in evaluations.
Bayesian structure learning allows inferring Bayesian network structure from data while reasoning about the epistemic uncertainty -- a key element towards enabling active causal discovery and designing interventions in real world systems. In this work, we propose a general, fully differentiable framework for Bayesian structure learning (DiBS) that operates in the continuous space of a latent probabilistic graph representation. Contrary to existing work, DiBS is agnostic to the form of the local conditional distributions and allows for joint posterior inference of both the graph structure and the conditional distribution parameters. This makes our formulation directly applicable to posterior inference of complex Bayesian network models, e.g., with nonlinear dependencies encoded by neural networks. Using DiBS, we devise an efficient, general purpose variational inference method for approximating distributions over structural models. In evaluations on simulated and real-world data, our method significantly outperforms related approaches to joint posterior inference.