Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks

TL;DR

This paper introduces a new representation called SCNF for Probabilistic Boolean Networks, enabling scalable learning and long-term dynamic predictions for large systems, with efficient sampling for multi-step transition inference.

Contribution

The paper proposes SCNF as an equivalent representation for PBNs, facilitating scalable learning and long-term behavior prediction in large-scale probabilistic networks.

Findings

SCNF enables scalable learning for large PBNs

Efficient sampling allows multi-step transition probability estimation

Improves understanding of long-term node activity levels

Abstract

Probabilistic Boolean Networks (PBNs) have been previously proposed so as to gain insights into complex dy- namical systems. However, identification of large networks and of the underlying discrete Markov Chain which describes their temporal evolution, still remains a challenge. In this paper, we introduce an equivalent representation for the PBN, the Stochastic Conjunctive Normal Form (SCNF), which paves the way to a scalable learning algorithm and helps predict long- run dynamic behavior of large-scale systems. Moreover, SCNF allows its efficient sampling so as to statistically infer multi- step transition probabilities which can provide knowledge on the activity levels of individual nodes in the long run.