Distributed Data Parallel Acceleration-Based Generative Adversarial Network for Fingerprint Generation

Abstract

In the expanding landscape of artificial intelligence, scaling model training to accommodate larger and more intricate neural networks and datasets is imperative. This study addresses the scaling issue by employing Distributed Data Parallel (DDP) frameworks to enhance the training of deep learning models, specifically focusing on the generation of synthetic fingerprints. Utilizing DDP enables efficient management of vast datasets essential for training generative models, ensuring comprehensive coverage of the variability inherent in fingerprints. Moreover, the application of DDP in fingerprint generation not only expedites the training process but also enhances data security by distributing computation across multiple nodes. The effectiveness of DDP is demonstrated through substantial improvements in training efficiency, as evidenced by reduced training times and balanced Graphics Processing Unit (GPU) utilization rates. However, the study reveals challenges in GPU underutilization with larger batch sizes, indicating opportunities for optimizing resource allocation. Advances in Deep Convolutional Generative Adversarial Network (DCGAN) architecture is also discussed, highlighting the model's capability to create realistic synthetic fingerprints and suggesting a future focus on algorithmic adaptability and network sophistication.