MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compression
This addresses the challenge of deploying compressed neural networks on edge devices by providing an incremental verification method, though it is incremental in nature.
The paper tackled the problem of verifying compressed deep neural networks (e.g., via quantization and pruning) for safety and reliability, presenting MUC-G4, which achieved high proof reuse rates and significant speedup in verification time compared to traditional methods.
The rapid development of deep learning has led to challenges in deploying neural networks on edge devices, mainly due to their high memory and runtime complexity. Network compression techniques, such as quantization and pruning, aim to reduce this complexity while maintaining accuracy. However, existing incremental verification methods often focus only on quantization and struggle with structural changes. This paper presents MUC-G4 (Minimal Unsat Core-Guided Incremental Verification), a novel framework for incremental verification of compressed deep neural networks. It encodes both the original and compressed networks into SMT formulas, classifies changes, and use \emph{Minimal Unsat Cores (MUCs)} from the original network to guide efficient verification for the compressed network. Experimental results show its effectiveness in handling quantization and pruning, with high proof reuse rates and significant speedup in verification time compared to traditional methods. MUC-G4 hence offers a promising solution for ensuring the safety and reliability of compressed neural networks in practical applications.