In this paper, we propose IMA-GNN as an In-Memory Accelerator for centralized and decentralized Graph Neural Network inference, explore its potential in both settings and provide a guideline for the community targeting flexible and efficient edge computation. Leveraging IMA-GNN, we first model the computation and communication latencies of edge devices. We then present practical case studies on GNN-based taxi demand and supply prediction and also adopt four large graph datasets to quantitatively compare and analyze centralized and decentralized settings. Our cross-layer simulation results demonstrate that on average, IMA-GNN in the centralized setting can obtain ~790x communication speed-up compared to the decentralized GNN setting. However, the decentralized setting performs computation ~1400x faster while reducing the power consumption per device. This further underlines the need for a hybrid semi-decentralized GNN approach.
@article{arxiv.2303.14162,
title = {IMA-GNN: In-Memory Acceleration of Centralized and Decentralized Graph Neural Networks at the Edge},
author = {Mehrdad Morsali and Mahmoud Nazzal and Abdallah Khreishah and Shaahin Angizi},
journal= {arXiv preprint arXiv:2303.14162},
year = {2023}
}