Common wisdom in the graph neural network (GNN) community dictates that
anisotropic models -- in which messages sent between nodes are a function of
both the source and target node -- are required to achieve state-of-the-art
performance. Benchmarks to date have demonstrated that these models perform
better than comparable isotropic models -- where messages are a function of the
source node only. In this work we provide empirical evidence challenging this
narrative: we propose an isotropic GNN, which we call Efficient Graph
Convolution (EGC), that consistently outperforms comparable anisotropic models,
including the popular GAT or PNA architectures by using spatially-varying
adaptive filters. In addition to raising important questions for the GNN
community, our work has significant real-world implications for efficiency. EGC
achieves higher model accuracy, with lower memory consumption and latency,
along with characteristics suited to accelerator implementation, while being a
drop-in replacement for existing architectures. As an isotropic model, it
requires memory proportional to the number of vertices in the graph
($\mathcal{O}(V)$); in contrast, anisotropic models require memory proportional
to the number of edges ($\mathcal{O}(E)$). We demonstrate that EGC outperforms
existing approaches across 6 large and diverse benchmark datasets, and conclude
by discussing questions that our work raise for the community going forward.
Code and pretrained models for our experiments are provided at
this https URL

本文介绍了 Efficient Graph Convolution（EGC），它是一种等向性图神经网络，通过使用空间可变自适应滤波器，始终优于可比较的非等向性模型，包括流行的 GAT 或 PNA 结构，提高了模型精度，降低了内存消耗和延迟，并具有加速器实现的特点，适合于现有结构的替代方案，并讨论了我们工作对社区提出的重要问题。