Pruned Graph Neural Networks for Efficient Edge Classification and Fast Inference

Optimizing Graph Neural Networks (GNNs) inference is important for various applications, including High-Energy Physics experiments, natural language processing, and point cloud analysis. Effective optimization techniques, such as pruning, model reduction, automatic mixed precision, and advanced compilation strategies, improve inference speed and memory efficiency significantly. These methods are crucial for deploying GNNs in resource-constrained environments, ensuring scalability and real-time responses. In an experimental setting, using the TrackML dataset and applying these techniques to GNN models yielded promising results. Pruning and model reduction, in particular, emerged as the most impactful methods, leading to a 53% reduction in inference time and a 42% decrease in overall memory usage. These improvements demonstrate the potential of customized optimizations in improving GNN performance, making them more feasible for various real-world applications where computational efficiency is very important.