Optimization of multi-objectives for Adaptive Reverse Recommendation method on edge devices

The Neural Architecture Search (NAS) enables Deep Learning engineers to automatically explore the wide variety of all possible neural architectures to design the solution for a given problem. Though the NAS methods automatically generate the best possible architecture, it is time-consuming, and resource constraint since the search space consists of the best architectures(good accuracy) and includes non performing architectures as well. Researchers have proposed various NAS methods especially based on evolutionary algorithms which consists of diverse search space due to the presence of genetic operations leading to expensive search time cost. These NAS methods also deal with multiple objectives like FLOPS, latency and power usage, and model accuracy, for image classification tasks. Though the generated architectures from NAS have multi-objective, they require significant computing resources and are not suitable for running on edge devices with limited computational resources. The proposed method includes a novel model optimization method designed for the neural architecture generated from NAS methods to make it smaller in size, memory efficient, and faster at inference with minimal loss of accuracy. We optimized the models designed for standard datasets and decreased the parameters by 7.82% for CIFAR-10, 2.95% for CIFAR-100, 6.36% for STL-10, and 3.57% for Food-101 datasets. The resulting models have achieved an accuracy of 97.4% for CIFAR-10, 86% for CIFAR-100, 96.7% for STL-10, and 87.4% for Food-101 datasets.