Parallelization Techniques for Verifying Neural Networks

TL;DR

This paper presents parallelization strategies and heuristics to enhance the scalability of neural network verification, including partitioning methods and a pre-processing algorithm, demonstrated through extensive experiments and cloud-based scaling.

Contribution

It introduces novel parallelization techniques and heuristics for neural network verification, leveraging input space partitioning and neuron activation phases for improved scalability.

Findings

Enhanced verification scalability on benchmarks

Effective partitioning strategies demonstrated

Promising results with cloud-based ultra-scaling

Abstract

Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parallel computing to improve the scalability of neural network verification. We introduce an algorithm based on partitioning the verification problem in an iterative manner and explore two partitioning strategies, that work by partitioning the input space or by case splitting on the phases of the neuron activations, respectively. We also introduce a highly parallelizable pre-processing algorithm that uses the neuron activation phases to simplify the neural network verification problems. An extensive experimental evaluation shows the benefit of these techniques on both existing benchmarks and new benchmarks from the aviation domain. A preliminary experiment with ultra-scaling our algorithm using a large distributed cloud-based platform also shows promising results.