Counterexample Guided Neural Network Quantization Refinement

João Batista P. Matos, Eddie B. de Lima Filho, Iury Bessa, Edoardo Manino, Xidan Song, Lucas C. Cordeiro

2023IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems18 citationsDOI Open Access PDF

Abstract

Deploying Neural networks (NNs) in low-resource domains is challenging because of their high computing, memory, and power requirements. For this reason, NNs are often quantized before deployment, but such an approach degrades their accuracy. Thus, we propose the counterexample guided neural network quantization refinement (CEG4N) framework, which combines search-based quantization and equivalence checking. The former minimizes computational requirements, while the latter guarantees that the behavior of an NN does not change after quantization. We evaluate CEG4N on a diverse set of benchmarks, including large and small NNs. Our technique successfully quantizes the networks in the chosen evaluation set, while producing models with up to 163% better accuracy than state-of-the-art techniques.

Topics & Concepts

CounterexampleQuantization (signal processing)Artificial neural networkComputer scienceEquivalence (formal languages)Deep neural networksTheoretical computer scienceAlgorithmArtificial intelligenceMathematicsDiscrete mathematicsAdversarial Robustness in Machine LearningAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning