Litcius/Paper detail

FTT-NAS: Discovering Fault-Tolerant Neural Architecture

Wenshuo Li, Xuefei Ning, Guangjun Ge, Xiaoming Chen, Yu Wang, Huazhong Yang

202035 citationsDOI

Abstract

With the fast evolvement of deep-learning specific embedded computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying NNs onto the edge devices under complex environments, there are various types of possible faults: soft errors caused by atmospheric neutrons and radioactive impurities, voltage instability, aging, temperature variations, and malicious attackers. Thus the safety risk of deploying neural networks at edge computing devices in safety-critic applications is now drawing much attention. In this paper, we implement the random bit-flip, Gaussian, and Salt-and-Pepper fault models and establish a multi-objective fault-tolerant neural architecture search framework. On top of the NAS framework, we propose Fault-Tolerant Neural Architecture Search (FT-NAS) to automatically discover convolutional neural network (CNN) architectures that are reliable to various faults in nowadays edge devices. Then we incorporate fault-tolerant training (FTT) in the search process to achieve better results, which we called FTT-NAS. Experiments show that the discovered architecture FT-NAS-Net and FTT-NAS-Net outperform other hand-designed baseline architectures (58.1%/86.6% VS. 10.0%/52.2%), with comparable FLOPs and less parameters. What is more, the architectures trained under a single fault model can also defend against other faults. By inspecting the discovered architecture, we find that there are redundant connections learned to protect the sensitive paths. This insight can guide future fault-tolerant neural architecture design, and we verify it by a modification on ResNet-20-ResNet-M.

Topics & Concepts

Computer scienceConvolutional neural networkEnhanced Data Rates for GSM EvolutionDeep learningFault toleranceEdge computingEdge deviceArtificial neural networkFault (geology)ArchitectureArtificial intelligenceDistributed computingCloud computingMargin (machine learning)Process (computing)Embedded systemMachine learningArtGeologyOperating systemVisual artsSeismologyAdversarial Robustness in Machine LearningAdvanced Neural Network ApplicationsAnomaly Detection Techniques and Applications