Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms
This addresses memory constraints for deploying GNNs on edge devices, but it is incremental as it optimizes existing methods rather than introducing a new paradigm.
The paper tackled the poor efficiency and frequent Out-Of-Memory problems in Graph Neural Network inference on edge computing platforms by proposing a feature decomposition approach, resulting in up to 3x speedup and up to 5x memory efficiency improvement.
Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-Of-Memory (OOM) problem limit the successful application of GNN on edge computing platforms. To tackle these problems, a feature decomposition approach is proposed for memory efficiency optimization of GNN inference. The proposed approach could achieve outstanding optimization on various GNN models, covering a wide range of datasets, which speeds up the inference by up to 3x. Furthermore, the proposed feature decomposition could significantly reduce the peak memory usage (up to 5x in memory efficiency improvement) and mitigate OOM problems during GNN inference.