LGNov 1, 2022

Efficient Graph Neural Network Inference at Large Scale

arXiv:2211.00495v39 citationsh-index: 77
Originality Highly original
AI Analysis

This addresses scalability issues for real-time GNN applications in domains like social networks or recommendation systems, offering a flexible trade-off between latency and accuracy.

The paper tackles the problem of slow graph neural network inference on large-scale graphs by proposing an adaptive propagation order approach and Inception Distillation, achieving a 75x speedup on the Ogbn-products dataset while maintaining or improving accuracy.

Graph neural networks (GNNs) have demonstrated excellent performance in a wide range of applications. However, the enormous size of large-scale graphs hinders their applications under real-time inference scenarios. Although existing scalable GNNs leverage linear propagation to preprocess the features and accelerate the training and inference procedure, these methods still suffer from scalability issues when making inferences on unseen nodes, as the feature preprocessing requires the graph is known and fixed. To speed up the inference in the inductive setting, we propose a novel adaptive propagation order approach that generates the personalized propagation order for each node based on its topological information. This could successfully avoid the redundant computation of feature propagation. Moreover, the trade-off between accuracy and inference latency can be flexibly controlled by simple hyper-parameters to match different latency constraints of application scenarios. To compensate for the potential inference accuracy loss, we further propose Inception Distillation to exploit the multi scale reception information and improve the inference performance. Extensive experiments are conducted on four public datasets with different scales and characteristics, and the experimental results show that our proposed inference acceleration framework outperforms the SOTA graph inference acceleration baselines in terms of both accuracy and efficiency. In particular, the advantage of our proposed method is more significant on larger-scale datasets, and our framework achieves $75\times$ inference speedup on the largest Ogbn-products dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes