Approximate Model Counting by Partial Knowledge Compilation

TL;DR

This paper introduces PartialKC, a novel approximate model counting method using partial Decision-DNNF, which improves accuracy and scalability over existing sampling techniques by leveraging knowledge compilation and importance sampling.

Contribution

It proposes a generalized partial Decision-DNNF with unknown vertices and an algorithm for unbiased model count estimation, enhancing efficiency and accuracy.

Findings

PartialKC outperforms SampleSearch and SearchTreeSampler in accuracy.

PartialKC scales better than SearchTreeSampler.

Knowledge compilation accelerates sampling processes.

Abstract

Model counting is the problem of computing the number of satisfying assignments of a given propositional formula. Although exact model counters can be naturally furnished by most of the knowledge compilation (KC) methods, in practice, they fail to generate the compiled results for the exact counting of models for certain formulas due to the explosion in sizes. Decision-DNNF is an important KC language that captures most of the practical compilers. We propose a generalized Decision-DNNF (referred to as partial Decision-DNNF) via introducing a class of new leaf vertices (called unknown vertices), and then propose an algorithm called PartialKC to generate randomly partial Decision-DNNF formulas from the given formulas. An unbiased estimate of the model number can be computed via a randomly partial Decision-DNNF formula. Each calling of PartialKC consists of multiple callings of MicroKC, while each of the latter callings is a process of importance sampling equipped with KC technologies. The experimental results show that PartialKC is more accurate than both SampleSearch and SearchTreeSampler, PartialKC scales better than SearchTreeSampler, and the KC technologies can obviously accelerate sampling.