Danghui Wang

A Thread-Saving Schedule with Graph Analysis for Parallel Deep Learning Applications on Embedded Systems

2018

The training of neural networks in embedded systems has become the direction of development nowadays. Because of the limited resources of embedded systems, it is not friendly to resource-consuming model training. What is more unfortunate …

CiliaGraph: Enabling Expression-enhanced Hyper-Dimensional Computation in Ultra-Lightweight and One-Shot Graph Classification on Edge

2024 · arXiv (Cornell University)

Graph Neural Networks (GNNs) are computationally demanding and inefficient when applied to graph classification tasks in resource-constrained edge scenarios due to their inherent process, involving multiple rounds of forward and backward propagation. As a lightweight …