MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment

arXiv:2402.13525v1 Announce Type: new
Abstract: Recent years have seen the explosion of edge intelligence with powerful Deep Neural Networks (DNNs). One popular scheme is training DNNs on powerful cloud servers and subsequently porting them to mobile devices after being lightweight. Conventional approaches manually specialized DNNs for various edge platforms and retrain them with real-world data. However, as the number of platforms increases, these approaches become labour-intensive and computationally prohibitive. Additionally, real-world data tends to be sparse-label, further increasing the difficulty …

abstract arxiv cloud cs.dc cs.lg data deep neural network deployment devices edge edge ai edge intelligence intelligence mobile mobile devices network networks neural network neural networks popular servers them training type via